Nick Hawes

Alexander Rutherford, Benjamin Ellis, Matteo Gallici et al. · deepmind, meta-ai

Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally, RL environments run on the CPU, which limits their scalability with typical academic compute. However, recent advancements in JAX have enabled the wider use of hardware acceleration, enabling massively parallel RL training pipelines and environments. While this has been successfully applied to single-agent RL, it has not yet been widely adopted for multi-agent scenarios. In this paper, we present JaxMARL, the first open-source, Python-based library that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments and popular baseline algorithms. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is around 14 times faster than existing approaches, and up to 12500x when multiple training runs are vectorized. This enables efficient and thorough evaluations, potentially alleviating the evaluation crisis in the field. We also introduce and benchmark SMAX, a JAX-based approximate reimplementation of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. The code is available at https://github.com/flairox/jaxmarl.

Alexander Rutherford, Michael Beukman, Timon Willi et al.

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. Surprisingly, despite methods aiming to maximise regret in theory, the practical approximations do not correlate with regret but with success rate. As a result, a significant portion of an agent's experience comes from environments it has already mastered, offering little to no contribution toward enhancing its abilities. Put differently, current methods fail to predict intuitive measures of ``learnability.'' Specifically, they are unable to consistently identify those scenarios that the agent can sometimes solve, but not always. Based on our analysis, we develop a method that directly trains on scenarios with high learnability. This simple and intuitive approach outperforms existing UED methods in several binary-outcome environments, including the standard domain of Minigrid and a novel setting closely inspired by a real-world robotics problem. We further introduce a new adversarial evaluation procedure for directly measuring robustness, closely mirroring the conditional value at risk (CVaR). We open-source all our code and present visualisations of final policies here: https://github.com/amacrutherford/sampling-for-learnability.

Marc Rigter, Bruno Lacerda, Nick Hawes · oxford

We consider robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control. In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time. This cost represents the human time required to teleoperate the robot, or recover the robot from failures. For each episode, the agent must choose between requesting human teleoperation, or using one of its autonomous controllers. In our approach, we learn to predict the success probability for each controller, given the initial state of an episode. This is used in a contextual multi-armed bandit algorithm to choose the controller for the episode. A controller is learnt online from demonstrations and reinforcement learning so that autonomous performance improves, and the system becomes less reliant on the teleoperator with more experience. We show that our approach to controller selection reduces the human cost to perform two simulated tasks and a single real-world task.

Roland Ilyes, Lara Brudermüller, Nick Hawes et al.

Signal Temporal Logic (STL) robustness is a common objective for optimal robot control, but its dependence on history limits the robot's decision-making capabilities when used in Model Predictive Control (MPC) approaches. In this work, we introduce Signal Temporal Logic robustness-to-go (Ro-To-Go), a new quantitative semantics for the logic that isolates the contributions of suffix trajectories. We prove its relationship to formula progression for Metric Temporal Logic, and show that the robustness-to-go depends only on the suffix trajectory and progressed formula. We implement robustness-to-go as the objective in an MPC algorithm and use formula progression to efficiently evaluate it online. We test the algorithm in simulation and compare it to MPC using traditional STL robustness. Our experiments show that using robustness-to-go results in a higher success rate.

Daniel Omeiza, Raunak Bhattacharyya, Nick Hawes et al. · oxford

The nature of explanations provided by an explainable AI algorithm has been a topic of interest in the explainable AI and human-computer interaction community. In this paper, we investigate the effects of natural language explanations' specificity on passengers in autonomous driving. We extended an existing data-driven tree-based explainer algorithm by adding a rule-based option for explanation generation. We generated auditory natural language explanations with different levels of specificity (abstract and specific) and tested these explanations in a within-subject user study (N=39) using an immersive physical driving simulation setup. Our results showed that both abstract and specific explanations had similar positive effects on passengers' perceived safety and the feeling of anxiety. However, the specific explanations influenced the desire of passengers to takeover driving control from the autonomous vehicle (AV), while the abstract explanations did not. We conclude that natural language auditory explanations are useful for passengers in autonomous driving, and their specificity levels could influence how much in-vehicle participants would wish to be in control of the driving activity.

Branton DeMoss, Paul Duckworth, Jakob Foerster et al.

For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which addresses all three of these problems. DITTO optimizes a novel distance metric in the latent space of a learned world model: First, we train a world model on all available trajectory data, then, the imitation agent is unrolled from expert start states in the learned model, and penalized for its latent divergence from the expert dataset over multiple time steps. We optimize this multi-step latent divergence using standard reinforcement learning algorithms, which provably induces imitation learning, and empirically achieves state-of-the art performance and sample efficiency on a range of Atari environments from pixels, without any online environment access. We also adapt other standard imitation learning algorithms to the world model setting, and show that this considerably improves their performance. Our results show how creative use of world models can lead to a simple, robust, and highly-performant policy-learning framework.

Marc Rigter, Bruno Lacerda, Nick Hawes

Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy optimisation within that model, have emerged as a promising approach to this problem. In this work, we present Robust Adversarial Model-Based Offline RL (RAMBO), a novel approach to model-based offline RL. We formulate the problem as a two-player zero sum game against an adversarial environment model. The model is trained to minimise the value function while still accurately predicting the transitions in the dataset, forcing the policy to act conservatively in areas not covered by the dataset. To approximately solve the two-player game, we alternate between optimising the policy and adversarially optimising the model. The problem formulation that we address is theoretically grounded, resulting in a probably approximately correct (PAC) performance guarantee and a pessimistic value function which lower bounds the value function in the true environment. We evaluate our approach on widely studied offline RL benchmarks, and demonstrate that it outperforms existing state-of-the-art baselines.

Harry Mead, Bruno Lacerda, Jakob Foerster et al.

Unsupervised Environment Design (UED) seeks to automatically generate training curricula for reinforcement learning (RL) agents, with the goal of improving generalisation and zero-shot performance. However, designing effective curricula remains a difficult problem, particularly in settings where small subsets of environment parameterisations result in significant increases in the complexity of the required policy. Current methods struggle with a difficult credit assignment problem and rely on regret approximations that fail to identify challenging levels, both of which are compounded as the size of the environment grows. We propose Dynamic Environment Generation for UED (DEGen) to enable a denser level generator reward signal, reducing the difficulty of credit assignment and allowing for UED to scale to larger environment sizes. We also introduce a new regret approximation, Maximised Negative Advantage (MNA), as a significantly improved metric to optimise for, that better identifies more challenging levels. We show empirically that MNA outperforms current regret approximations and when combined with DEGen, consistently outperforms existing methods, especially as the size of the environment grows. We have made all our code available here: https://github.com/HarryMJMead/Dynamic-Environment-Generation-for-UED.

Marc Rigter, Bruno Lacerda, Nick Hawes

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic outcomes. In other words, decision-making should be risk-sensitive. Previous works on risk in offline RL combine together offline RL techniques, to avoid distributional shift, with risk-sensitive RL algorithms, to achieve risk-sensitivity. In this work, we propose risk-sensitivity as a mechanism to jointly address both of these issues. Our model-based approach is risk-averse to both epistemic and aleatoric uncertainty. Risk-aversion to epistemic uncertainty prevents distributional shift, as areas not covered by the dataset have high epistemic uncertainty. Risk-aversion to aleatoric uncertainty discourages actions that may result in poor outcomes due to environment stochasticity. Our experiments show that our algorithm achieves competitive performance on deterministic benchmarks, and outperforms existing approaches for risk-sensitive objectives in stochastic domains.

Michael Groom, Victor-Alexandru Darvariu, Lars Kunze et al.

Unlike standard expected-return Reinforcement Learning (RL), Distributional RL (DRL) models the full return distribution, making it better-suited for uncertainty-aware and risk-sensitive decision-making. Conditional Flow Matching (CFM) critics have recently attracted attention for modelling continuous, multi-modal return distributions. Despite this interest, there remains a substantial metric mismatch: DRL theory relies on the distributional Bellman operator being contractive in the $p$-Wasserstein distance, yet existing CFM critics are trained with arbitrary source-target couplings, so their flow-matching losses are not Wasserstein-aligned surrogates for matching Bellman target return distributions. In this work, we address this mismatch by proposing FlowIQN, a CFM critic that sorts source and Bellman target samples within each mini-batch to approximate the monotone optimal transport coupling, replacing arbitrary pairings with quantile-aligned flow paths. We prove that the loss of our quantile-coupled CFM critic yields a Wasserstein-aligned approximate projection compatible with the foundations of DRL. To our knowledge, FlowIQN is the first flow-matching distributional critic with an explicit Wasserstein-aligned projection guarantee. We further extend FlowIQN with shortcut models for efficient inference. Empirical results show that FlowIQN improves Wasserstein return-distribution accuracy over other CFM critics. It also yields competitive performance on offline RL benchmarks across multiple policy extraction methods, providing a theoretically grounded CFM critic that is readily compatible with DRL pipelines. Code: https://github.com/ori-goals/flowIQN.

Victor-Alexandru Darvariu, Charlotte Z. Reed, Jan Stratmann et al.

Underwater glider robots have become an indispensable tool for ocean sampling. Although stakeholders are calling for tools to manage increasingly large fleets of gliders, successful autonomous long-term deployments have thus far been scarce, which hints at a lack of suitable methodologies and systems. In this work, we formulate glider navigation planning as a stochastic shortest-path Markov Decision Process and propose a sample-based online planner based on Monte Carlo Tree Search. Samples are generated by a physics-informed simulator that captures uncertain execution of controls and ocean current forecasts while remaining computationally tractable. The simulator parameters are fitted using historical glider data. We integrate these methods into an autonomous command-and-control system for Slocum gliders that enables closed-loop replanning at each surfacing. The resulting system was validated in two field deployments in the North Sea totalling approximately 3 months and 1000 km of autonomous operation. Results demonstrate improved efficiency compared to straight-to-goal navigation and show the practicality of sample-based planning for long-term marine autonomy.

Junlin Xiao, Victor-Alexandru Darvariu, Bruno Lacerda et al.

Monte Carlo Tree Search is a cornerstone algorithm for online planning, and its root-parallel variant is widely used when wall clock time is limited but best performance is desired. In environments with continuous action spaces, how to best aggregate statistics from different threads is an important yet underexplored question. In this work, we introduce a method that uses Gaussian Process Regression to obtain value estimates for promising actions that were not trialed in the environment. We perform a systematic evaluation across 6 different domains, demonstrating that our approach outperforms existing aggregation strategies while requiring a modest increase in inference time.

Yang You, Ufuk Çakır, Alex Schutz et al.

The value function of a POMDP exhibits the piecewise-linear-convex (PWLC) property and can be represented as a finite set of hyperplanes, known as $α$-vectors. Most state-of-the-art POMDP solvers (offline planners) follow the point-based value iteration scheme, which performs Bellman backups on $α$-vectors at reachable belief points until convergence. However, since each $α$-vector is $|S|$-dimensional, these methods quickly become intractable for large-scale problems due to the prohibitive computational cost of Bellman backups. In this work, we demonstrate that the PWLC property allows a POMDP's value function to be alternatively represented as a finite set of neural networks. This insight enables a novel POMDP planning algorithm called \emph{Neural Value Iteration}, which combines the generalization capability of neural networks with the classical value iteration framework. Our approach achieves near-optimal solutions even in extremely large POMDPs that are intractable for existing offline solvers.

Harry Mead, Clarissa Costen, Bruno Lacerda et al.

When optimising for conditional value at risk (CVaR) using policy gradients (PG), current methods rely on discarding a large proportion of trajectories, resulting in poor sample efficiency. We propose a reformulation of the CVaR optimisation problem by capping the total return of trajectories used in training, rather than simply discarding them, and show that this is equivalent to the original problem if the cap is set appropriately. We show, with empirical results in an number of environments, that this reformulation of the problem results in consistently improved performance compared to baselines. We have made all our code available here: https://github.com/HarryMJMead/cvar-return-capping.

Daniel Omeiza, Raunak Bhattacharyya, Marina Jirotka et al.

Transparency in automated systems could be afforded through the provision of intelligible explanations. While transparency is desirable, might it lead to catastrophic outcomes (such as anxiety), that could outweigh its benefits? It's quite unclear how the specificity of explanations (level of transparency) influences recipients, especially in autonomous driving (AD). In this work, we examined the effects of transparency mediated through varying levels of explanation specificity in AD. We first extended a data-driven explainer model by adding a rule-based option for explanation generation in AD, and then conducted a within-subject lab study with 39 participants in an immersive driving simulator to study the effect of the resulting explanations. Specifically, our investigation focused on: (1) how different types of explanations (specific vs. abstract) affect passengers' perceived safety, anxiety, and willingness to take control of the vehicle when the vehicle perception system makes erroneous predictions; and (2) the relationship between passengers' behavioural cues and their feelings during the autonomous drives. Our findings showed that passengers felt safer with specific explanations when the vehicle's perception system had minimal errors, while abstract explanations that hid perception errors led to lower feelings of safety. Anxiety levels increased when specific explanations revealed perception system errors (high transparency). We found no significant link between passengers' visual patterns and their anxiety levels. Our study suggests that passengers prefer clear and specific explanations (high transparency) when they originate from autonomous vehicles (AVs) with optimal perceptual accuracy.

Lara Brudermüller, Guillaume Berger, Julius Jankowski et al.

Reliable robot autonomy hinges on decision-making systems that account for uncertainty without imposing overly conservative restrictions on the robot's action space. We introduce Chance-Constrained Via-Point-Based Stochastic Trajectory Optimisation (CC-VPSTO), a real-time capable framework for generating task-efficient robot trajectories that satisfy constraints with high probability by formulating stochastic control as a chance-constrained optimisation problem. Since such problems are generally intractable, we propose a deterministic surrogate formulation based on Monte Carlo sampling, solved efficiently with gradient-free optimisation. To address bias in naïve sampling approaches, we quantify approximation error and introduce padding strategies to improve reliability. We focus on three challenges: (i) sample-efficient constraint approximation, (ii) conditions for surrogate solution validity, and (iii) online optimisation. Integrated into a receding-horizon MPC framework, CC-VPSTO enables reactive, task-efficient control under uncertainty, balancing constraint satisfaction and performance in a principled manner. The strengths of our approach lie in its generality, i.e. no assumptions on the underlying uncertainty distribution, system dynamics, cost function, or the form of inequality constraints; and its applicability to online robot motion planning. We demonstrate the validity and efficiency of our approach in both simulation and on a Franka Emika robot.

Michael Painter, Mohamed Baioumy, Nick Hawes et al. · oxford

Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound applied to Trees (UCT), are instrumental to automated planning techniques. However, UCT can be slow to explore an optimal action when it initially appears inferior to other actions. Maximum ENtropy Tree-Search (MENTS) incorporates the maximum entropy principle into an MCTS approach, utilising Boltzmann policies to sample actions, naturally encouraging more exploration. In this paper, we highlight a major limitation of MENTS: optimal actions for the maximum entropy objective do not necessarily correspond to optimal actions for the original objective. We introduce two algorithms, Boltzmann Tree Search (BTS) and Decaying ENtropy Tree-Search (DENTS), that address these limitations and preserve the benefits of Boltzmann policies, such as allowing actions to be sampled faster by using the Alias method. Our empirical analysis shows that our algorithms show consistent high performance across several benchmark domains, including the game of Go.

Branton DeMoss, Silvia Sapora, Jakob Foerster et al.

We demonstrate the existence of a complexity phase transition in neural networks by studying the grokking phenomenon, where networks suddenly transition from memorization to generalization long after overfitting their training data. To characterize this phase transition, we introduce a theoretical framework for measuring complexity based on rate-distortion theory and Kolmogorov complexity, which can be understood as principled lossy compression for networks. We find that properly regularized networks exhibit a sharp phase transition: complexity rises during memorization, then falls as the network discovers a simpler underlying pattern that generalizes. In contrast, unregularized networks remain trapped in a high-complexity memorization phase. We establish an explicit connection between our complexity measure and generalization bounds, providing a theoretical foundation for the link between lossy compression and generalization. Our framework achieves compression ratios 30-40x better than naïve approaches, enabling precise tracking of complexity dynamics. Finally, we introduce a regularization method based on spectral entropy that encourages networks toward low-complexity representations by penalizing their intrinsic dimension.

Iman Nematollahi, Branton DeMoss, Akshay L Chandra et al.

We introduce LUMOS, a language-conditioned multi-task imitation learning framework for robotics. LUMOS learns skills by practicing them over many long-horizon rollouts in the latent space of a learned world model and transfers these skills zero-shot to a real robot. By learning on-policy in the latent space of the learned world model, our algorithm mitigates policy-induced distribution shift which most offline imitation learning methods suffer from. LUMOS learns from unstructured play data with fewer than 1% hindsight language annotations but is steerable with language commands at test time. We achieve this coherent long-horizon performance by combining latent planning with both image- and language-based hindsight goal relabeling during training, and by optimizing an intrinsic reward defined in the latent space of the world model over multiple time steps, effectively reducing covariate shift. In experiments on the difficult long-horizon CALVIN benchmark, LUMOS outperforms prior learning-based methods with comparable approaches on chained multi-task evaluations. To the best of our knowledge, we are the first to learn a language-conditioned continuous visuomotor control for a real-world robot within an offline world model. Videos, dataset and code are available at http://lumos.cs.uni-freiburg.de.

Alex Schutz, Yang You, Matias Mattamala et al.

Deterministic partially observable Markov decision processes (DetPOMDPs) often arise in planning problems where the agent is uncertain about its environmental state but can act and observe deterministically. In this paper, we propose DetMCVI, an adaptation of the Monte Carlo Value Iteration (MCVI) algorithm for DetPOMDPs, which builds policies in the form of finite-state controllers (FSCs). DetMCVI solves large problems with a high success rate, outperforming existing baselines for DetPOMDPs. We also verify the performance of the algorithm in a real-world mobile robot forest mapping scenario.

Rhys Howard, Nick Hawes, Lars Kunze

Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if one assumes agents act to maximise some concept of reward, it is difficult to make accurate causal inferences of agent planning without capturing what is of importance to the agent. Thus our work aims to learn a weighting of reward metrics for agents such that explanations for agent interactions can be causally inferred. We validate our approach quantitatively and qualitatively across three real-world driving datasets, demonstrating a functional improvement over previous methods and competitive performance across evaluation metrics.

Ufuk Çakır, Victor-Alexandru Darvariu, Bruno Lacerda et al.

Artificial intelligence methods are increasingly being explored for managing wildfires and other natural hazards. In particular, reinforcement learning (RL) is a promising path towards improving outcomes in such uncertain decision-making scenarios and moving beyond reactive strategies. However, training RL agents requires many environment interactions, and the speed of existing wildfire simulators is a severely limiting factor. We introduce $\texttt{JaxWildfire}$, a simulator underpinned by a principled probabilistic fire spread model based on cellular automata. It is implemented in JAX and enables vectorized simulations using $\texttt{vmap}$, allowing high throughput of simulations on GPUs. We demonstrate that $\texttt{JaxWildfire}$ achieves 6-35x speedup over existing software and enables gradient-based optimization of simulator parameters. Furthermore, we show that $\texttt{JaxWildfire}$ can be used to train RL agents to learn wildfire suppression policies. Our work is an important step towards enabling the advancement of RL techniques for managing natural hazards.

Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki et al.

Neural Algorithmic Reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning. Despite its successes, important limitations remain: inability to construct valid solutions without post-processing and to reason about multiple correct ones, poor performance on combinatorial NP-hard problems, and inapplicability to problems for which strong algorithms are not yet known. To address these limitations, we reframe the problem of learning algorithm trajectories as a Markov Decision Process, which imposes structure on the solution construction procedure and unlocks the powerful tools of imitation and reinforcement learning (RL). We propose the GNARL framework, encompassing the methodology to translate problem formulations from NAR to RL and a learning architecture suitable for a wide range of graph-based problems. We achieve very high graph accuracy results on several CLRS-30 problems, performance matching or exceeding much narrower NAR approaches for NP-hard problems and, remarkably, applicability even when lacking an expert algorithm.

Yang You, Alex Schutz, Zhikun Li et al.

Many high-level multi-agent planning problems, including multi-robot navigation and path planning, can be effectively modeled using deterministic actions and observations. In this work, we focus on such domains and introduce the class of Deterministic Decentralized POMDPs (Det-Dec-POMDPs). This is a subclass of Dec-POMDPs characterized by deterministic transitions and observations conditioned on the state and joint actions. We then propose a practical solver called Iterative Deterministic POMDP Planning (IDPP). This method builds on the classic Joint Equilibrium Search for Policies framework and is specifically optimized to handle large-scale Det-Dec-POMDPs that current Dec-POMDP solvers are unable to address efficiently.

Yang You, Vincent Thomas, Alex Schutz et al.

Currently, large partially observable Markov decision processes (POMDPs) are often solved by sampling-based online methods which interleave planning and execution phases. However, a pre-computed offline policy is more desirable in POMDP applications with time or energy constraints. But previous offline algorithms are not able to scale up to large POMDPs. In this article, we propose a new sampling-based algorithm, the partially observable Monte-Carlo graph search (POMCGS) to solve large POMDPs offline. Different from many online POMDP methods, which progressively develop a tree while performing (Monte-Carlo) simulations, POMCGS folds this search tree on the fly to construct a policy graph, so that computations can be drastically reduced, and users can analyze and validate the policy prior to embedding and executing it. Moreover, POMCGS, together with action progressive widening and observation clustering methods provided in this article, is able to address certain continuous POMDPs. Through experiments, we demonstrate that POMCGS can generate policies on the most challenging POMDPs, which cannot be computed by previous offline algorithms, and these policies' values are competitive compared with the state-of-the-art online POMDP algorithms.

Marc Rigter, Paul Duckworth, Bruno Lacerda et al.

Planning in Markov decision processes (MDPs) typically optimises the expected cost. However, optimising the expectation does not consider the risk that for any given run of the MDP, the total cost received may be unacceptably high. An alternative approach is to find a policy which optimises a risk-averse objective such as conditional value at risk (CVaR). However, optimising the CVaR alone may result in poor performance in expectation. In this work, we begin by showing that there can be multiple policies which obtain the optimal CVaR. This motivates us to propose a lexicographic approach which minimises the expected cost subject to the constraint that the CVaR of the total cost is optimal. We present an algorithm for this problem and evaluate our approach on four domains. Our results demonstrate that our lexicographic approach improves the expected cost compared to the state of the art algorithm, while achieving the optimal CVaR.

Fernando S. Barbosa, Bruno Lacerda, Paul Duckworth et al.

Recent trends envisage robots being deployed in areas deemed dangerous to humans, such as buildings with gas and radiation leaks. In such situations, the model of the underlying hazardous process might be unknown to the agent a priori, giving rise to the problem of planning for safe behaviour in partially known environments. We employ Gaussian process regression to create a probabilistic model of the hazardous process from local noisy samples. The result of this regression is then used by a risk metric, such as the Conditional Value-at-Risk, to reason about the safety at a certain state. The outcome is a risk function that can be employed in optimal motion planning problems. We demonstrate the use of the proposed function in two approaches. First is a sampling-based motion planning algorithm with an event-based trigger for online replanning. Second is an adaptation to the incremental Gaussian Process motion planner (iGPMP2), allowing it to quickly react and adapt to the environment. Both algorithms are evaluated in representative simulation scenarios, where they demonstrate the ability of avoiding high-risk areas.

Mohamed Baioumy, Corrado Pezzato, Carlos Hernandez Corbato et al.

This work presents a fault-tolerant control scheme for sensory faults in robotic manipulators based on active inference. In the majority of existing schemes, a binary decision of whether a sensor is healthy (functional) or faulty is made based on measured data. The decision boundary is called a threshold and it is usually deterministic. Following a faulty decision, fault recovery is obtained by excluding the malfunctioning sensor. We propose a stochastic fault-tolerant scheme based on active inference and precision learning which does not require a priori threshold definitions to trigger fault recovery. Instead, the sensor precision, which represents its health status, is learned online in a model-free way allowing the system to gradually, and not abruptly exclude a failing unit. Experiments on a robotic manipulator show promising results and directions for future work are discussed.

Mohamed Baioumy, Bruno Lacerda, Paul Duckworth et al.

Previous work on planning as active inference addresses finite horizon problems and solutions valid for online planning. We propose solving the general Stochastic Shortest-Path Markov Decision Process (SSP MDP) as probabilistic inference. Furthermore, we discuss online and offline methods for planning under uncertainty. In an SSP MDP, the horizon is indefinite and unknown a priori. SSP MDPs generalize finite and infinite horizon MDPs and are widely used in the artificial intelligence community. Additionally, we highlight some of the differences between solving an MDP using dynamic programming approaches widely used in the artificial intelligence community and approaches used in the active inference community.

Mohamed Baioumy, Corrado Pezzato, Riccardo Ferrari et al.

This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The proposed solution makes use of the sensory prediction errors in the free-energy for the generation of residuals and thresholds for fault detection and isolation of sensory faults, and it does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2-DOF manipulator are presented, and future directions to improve the current fault recovery approach are discussed.

Marc Rigter, Bruno Lacerda, Nick Hawes

In this work, we address risk-averse Bayes-adaptive reinforcement learning. We pose the problem of optimising the conditional value at risk (CVaR) of the total return in Bayes-adaptive Markov decision processes (MDPs). We show that a policy optimising CVaR in this setting is risk-averse to both the parametric uncertainty due to the prior distribution over MDPs, and the internal uncertainty due to the inherent stochasticity of MDPs. We reformulate the problem as a two-player stochastic game and propose an approximate algorithm based on Monte Carlo tree search and Bayesian optimisation. Our experiments demonstrate that our approach significantly outperforms baseline approaches for this problem.

Marc Rigter, Bruno Lacerda, Nick Hawes

The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for planning in UMDPs to find robust policies which are not overly conservative. In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. We introduce a Bellman equation to compute the regret for a policy. We propose a dynamic programming algorithm that utilises the regret Bellman equation, and show that it optimises minimax regret exactly for UMDPs with independent uncertainties. For coupled uncertainties, we extend our approach to use options to enable a trade off between computation and solution quality. We evaluate our approach on both synthetic and real-world domains, showing that it significantly outperforms existing baselines.

Mohamed Baioumy, Paul Duckworth, Bruno Lacerda et al.

This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators. It is based on the active inference framework, prominent in computational neuroscience as a theory of the brain, where behaviour arises from minimizing variational free-energy. The robotic manipulator shows adaptive and robust behaviour compared to state-of-the-art methods. Additionally, we show the exact relationship to classic methods such as PID control. Finally, we show that by learning a temporal parameter and model variances, our approach can deal with unmodelled dynamics, damps oscillations, and is robust against disturbances and poor initial parameters. The approach is validated on the `Franka Emika Panda' 7 DoF manipulator.

Michael Painter, Bruno Lacerda, Nick Hawes

This work investigates Monte-Carlo planning for agents in stochastic environments, with multiple objectives. We propose the Convex Hull Monte-Carlo Tree-Search (CHMCTS) framework, which builds upon Trial Based Heuristic Tree Search and Convex Hull Value Iteration (CHVI), as a solution to multi-objective planning in large environments. Moreover, we consider how to pose the problem of approximating multiobjective planning solutions as a contextual multi-armed bandits problem, giving a principled motivation for how to select actions from the view of contextual regret. This leads us to the use of Contextual Zooming for action selection, yielding Zooming CHMCTS. We evaluate our algorithm using the Generalised Deep Sea Treasure environment, demonstrating that Zooming CHMCTS can achieve a sublinear contextual regret and scales better than CHVI on a given computational budget.

Manolis Chiou, Nick Hawes, Rustam Stolkin

This paper presents an Expert-guided Mixed-Initiative Control Switcher (EMICS) for remotely operated mobile robots. The EMICS enables switching between different levels of autonomy during task execution initiated by either the human operator and/or the EMICS. The EMICS is evaluated in two disaster response inspired experiments, one with a simulated robot and test arena, and one with a real robot in a realistic environment. Analyses from the two experiments provide evidence that: a) Human-Initiative (HI) systems outperform systems with single modes of operation, such as pure teleoperation, in navigation tasks; b) in the context of the simulated robot experiment, Mixed-Initiative (MI) systems provide improved performance in navigation tasks, improved operator performance in cognitive demanding secondary tasks, and improved operator workload compared to HI. Results also reinforce previous human-robot interaction evidence regarding the importance of the operator's personality traits and their trust in the autonomous system. Lastly, our experiment on a physical robot provides empirical evidence that identify two major challenges for MI control: a) the design of context-aware MI control systems; and b) the conflict for control between the robot's MI control system and the operator. Insights regarding these challenges are discussed and ways to tackle them are proposed.

Lars Kunze, Nick Hawes, Tom Duckett et al.

Autonomous systems will play an essential role in many applications across diverse domains including space, marine, air, field, road, and service robotics. They will assist us in our daily routines and perform dangerous, dirty and dull tasks. However, enabling robotic systems to perform autonomously in complex, real-world scenarios over extended time periods (i.e. weeks, months, or years) poses many challenges. Some of these have been investigated by sub-disciplines of Artificial Intelligence (AI) including navigation & mapping, perception, knowledge representation & reasoning, planning, interaction, and learning. The different sub-disciplines have developed techniques that, when re-integrated within an autonomous system, can enable robots to operate effectively in complex, long-term scenarios. In this paper, we survey and discuss AI techniques as 'enablers' for long-term robot autonomy, current progress in integrating these techniques within long-running robotic systems, and the future challenges and opportunities for AI in long-term autonomy.

Fatma Faruq, Bruno Lacerda, Nick Hawes et al.

We propose novel techniques for task allocation and planning in multi-robot systems operating in uncertain environments. Task allocation is performed simultaneously with planning, which provides more detailed information about individual robot behaviour, but also exploits independence between tasks to do so efficiently. We use Markov decision processes to model robot behaviour and linear temporal logic to specify tasks and safety constraints. Building upon techniques and tools from formal verification, we show how to generate a sequence of multi-robot policies, iteratively refining them to reallocate tasks if individual robots fail, and providing probabilistic guarantees on the performance (and safe operation) of the team of robots under the resulting policy. We implement our approach and evaluate it on a benchmark multi-robot example.

Nizar Massouh, Francesca Babiloni, Tatiana Tommasi et al.

Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in time, and as such it is prone to aging, as well as dataset bias issues. Moving beyond fixed training datasets will lead to more robust visual systems, especially when deployed on robots in new environments which must train on the objects they encounter there. To make this possible, it is important to break free from the need for manual annotators. Recent work has begun to investigate how to use the massive amount of images available on the Web in place of manual image annotations. We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy. By combining these two results, we obtain a method for learning powerful deep object models automatically from the Web. We confirm the effectiveness of our approach through object categorization experiments using our Web-derived version of ImageNet on a popular robot vision benchmark database, and on a lifelong object discovery task on a mobile robot.

Nick Hawes, Chris Burbridge, Ferdian Jovan et al.

Thanks to the efforts of the robotics and autonomous systems community, robots are becoming ever more capable. There is also an increasing demand from end-users for autonomous service robots that can operate in real environments for extended periods. In the STRANDS project we are tackling this demand head-on by integrating state-of-the-art artificial intelligence and robotics research into mobile service robots, and deploying these systems for long-term installations in security and care environments. Over four deployments, our robots have been operational for a combined duration of 104 days autonomously performing end-user defined tasks, covering 116km in the process. In this article we describe the approach we have used to enable long-term autonomous operation in everyday environments, and how our robots are able to use their long run times to improve their own performance.