Paul Weng

Han Fang, Yize Huang, Yuheng Zhao et al.

Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models suffer from high inference latency, while flow-based methods often require complex architectural constraints. Although in image generation domain, the MeanFlow paradigm offers a path to single-step inference, its direct application to robotics is impeded by critical theoretical pathologies, specifically spectral bias and gradient starvation in low-velocity regimes. To overcome these limitations, we propose the One-step MeanFlow Policy (OMP), a novel framework designed for high-fidelity, real-time manipulation. We introduce a lightweight directional alignment mechanism to explicitly synchronize predicted velocities with true mean velocities. Furthermore, we implement a Differential Derivation Equation (DDE) to approximate the Jacobian-Vector Product (JVP) operator, which decouples forward and backward passes to significantly reduce memory complexity. Extensive experiments on the Adroit and Meta-World benchmarks demonstrate that OMP outperforms state-of-the-art methods in success rate and trajectory accuracy, particularly in high-precision tasks, while retaining the efficiency of single-step generation.

Junqi Qian, Paul Weng, Chenmien Tan

When applying reinforcement learning (RL) to a new problem, reward engineering is a necessary, but often difficult and error-prone task a system designer has to face. To avoid this step, we propose LR4GPM, a novel (deep) RL method that can optimize a global performance metric, which is supposed to be available as part of the problem description. LR4GPM alternates between two phases: (1) learning a (possibly vector) reward function used to fit the performance metric, and (2) training a policy to optimize an approximation of this performance metric based on the learned rewards. Such RL training is not straightforward since both the reward function and the policy are trained using non-stationary data. To overcome this issue, we propose several training tricks. We demonstrate the efficiency of LR4GPM on several domains. Notably, LR4GPM outperforms the winner of a recent autonomous driving competition organized at DAI'2020.

Jiangdong Fan, Hongcai He, Paul Weng et al.

A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstrations without strict quality requirements has emerged as a powerful paradigm to address this challenge. However, previous methods often fail to fully utilize their potential by discarding non-expert data. Our key insight is that even demonstrations that fall outside the expert distribution but outperform the learned policy can enhance policy performance. To utilize this potential, we propose a novel approach named imitation learning via meta-learning an action ranker (ILMAR). ILMAR implements weighted behavior cloning (weighted BC) on a limited set of expert demonstrations along with supplementary demonstrations. It utilizes the functional of the advantage function to selectively integrate knowledge from the supplementary demonstrations. To make more effective use of supplementary demonstrations, we introduce meta-goal in ILMAR to optimize the functional of the advantage function by explicitly minimizing the distance between the current policy and the expert policy. Comprehensive experiments using extensive tasks demonstrate that ILMAR significantly outperforms previous methods in handling suboptimal demonstrations. Code is available at https://github.com/F-GOD6/ILMAR.

Timo Kaufmann, Paul Weng, Viktor Bengs et al.

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinforcement learning (PbRL), it stands at the intersection of artificial intelligence and human-computer interaction. This positioning offers a promising avenue to enhance the performance and adaptability of intelligent systems while also improving the alignment of their objectives with human values. The training of large language models (LLMs) has impressively demonstrated this potential in recent years, where RLHF played a decisive role in directing the model's capabilities toward human objectives. This article provides a comprehensive overview of the fundamentals of RLHF, exploring the intricate dynamics between RL agents and human input. While recent focus has been on RLHF for LLMs, our survey adopts a broader perspective, examining the diverse applications and wide-ranging impact of the technique. We delve into the core principles that underpin RLHF, shedding light on the symbiotic relationship between algorithms and human feedback, and discuss the main research trends in the field. By synthesizing the current landscape of RLHF research, this article aims to provide researchers as well as practitioners with a comprehensive understanding of this rapidly growing field of research.

Jianshu Hu, Paul Weng, Yutong Ban

While a powerful and promising approach, deep reinforcement learning (DRL) still suffers from sample inefficiency, which can be notably improved by resorting to more sophisticated techniques to address the exploration-exploitation dilemma. One such technique relies on action persistence (i.e., repeating an action over multiple steps). However, previous work exploiting action persistence either applies a fixed strategy or learns additional value functions (or policy) for selecting the repetition number. In this paper, we propose a novel method to dynamically adjust the action persistence based on the current exploration status of the state space. In such a way, our method does not require training of additional value functions or policy. Moreover, the use of a smooth scheduling of the repeat probability allows a more effective balance between exploration and exploitation. Furthermore, our method can be seamlessly integrated into various basic exploration strategies to incorporate temporal persistence. Finally, extensive experiments on different DMControl tasks demonstrate that our state-novelty guided action persistence method significantly improves the sample efficiency.

Han Fang, Zhihao Song, Paul Weng et al.

Recently, deep reinforcement learning has shown promising results for learning fast heuristics to solve routing problems. Meanwhile, most of the solvers suffer from generalizing to an unseen distribution or distributions with different scales. To address this issue, we propose a novel architecture, called Invariant Nested View Transformer (INViT), which is designed to enforce a nested design together with invariant views inside the encoders to promote the generalizability of the learned solver. It applies a modified policy gradient algorithm enhanced with data augmentations. We demonstrate that the proposed INViT achieves a dominant generalization performance on both TSP and CVRP problems with various distributions and different problem scales.

Jianshu Hu, Yunpeng Jiang, Paul Weng

Various data augmentation techniques have been recently proposed in image-based deep reinforcement learning (DRL). Although they empirically demonstrate the effectiveness of data augmentation for improving sample efficiency or generalization, which technique should be preferred is not always clear. To tackle this question, we analyze existing methods to better understand them and to uncover how they are connected. Notably, by expressing the variance of the Q-targets and that of the empirical actor/critic losses of these methods, we can analyze the effects of their different components and compare them. We furthermore formulate an explanation about how these methods may be affected by choosing different data augmentation transformations in calculating the target Q-values. This analysis suggests recommendations on how to exploit data augmentation in a more principled way. In addition, we include a regularization term called tangent prop, previously proposed in computer vision, but whose adaptation to DRL is novel to the best of our knowledge. We evaluate our proposition and validate our analysis in several domains. Compared to different relevant baselines, we demonstrate that it achieves state-of-the-art performance in most environments and shows higher sample efficiency and better generalization ability in some complex environments.

Yuwen Zhang, Viet Tran, Paul Weng

In clinical machine learning, the coexistence of multiple models with comparable performance -- a manifestation of the Rashomon Effect -- poses fundamental challenges for trustworthy deployment and evaluation. Small, imbalanced, and noisy datasets, coupled with high-dimensional and weakly identified clinical features, amplify this multiplicity and make conventional validation schemes unreliable. As a result, selecting among equally performing models becomes uncertain, particularly when resource constraints and operational priorities are not considered by conventional metrics like F1 score. To address these issues, we propose two complementary tools for robust model assessment and selection: Intervention Efficiency (IE) and the Perturbation Validation Framework (PVF). IE is a capacity-aware metric that quantifies how efficiently a model identifies actionable true positives when only limited interventions are feasible, thereby linking predictive performance with clinical utility. PVF introduces a structured approach to assess the stability of models under data perturbations, identifying models whose performance remains most invariant across noisy or shifted validation sets. Empirical results on synthetic and real-world healthcare datasets show that using these tools facilitates the selection of models that generalize more robustly and align with capacity constraints, offering a new direction for tackling the Rashomon Effect in clinical settings.

Yunpeng Jiang, Jianshu Hu, Paul Weng et al.

Symmetry is pervasive in robotics and has been widely exploited to improve sample efficiency in deep reinforcement learning (DRL). However, existing approaches primarily focus on spatial symmetries, such as reflection, rotation, and translation, while largely neglecting temporal symmetries. To address this gap, we explore time reversal symmetry, a form of temporal symmetry commonly found in robotics tasks such as door opening and closing. We propose Time Reversal symmetry enhanced Deep Reinforcement Learning (TR-DRL), a framework that combines trajectory reversal augmentation and time reversal guided reward shaping to efficiently solve temporally symmetric tasks. Our method generates reversed transitions from fully reversible transitions, identified by a proposed dynamics-consistent filter, to augment the training data. For partially reversible transitions, we apply reward shaping to guide learning, according to successful trajectories from the reversed task. Extensive experiments on the Robosuite and MetaWorld benchmarks demonstrate that TR-DRL is effective in both single-task and multi-task settings, achieving higher sample efficiency and stronger final performance compared to baseline methods.

Han Fang, Paul Weng, Yutong Ban

Recently, deep reinforcement learning (DRL) has achieved promising results in solving online 3D Bin Packing Problems (3D-BPP). However, these DRL-based policies may perform poorly on new instances due to distribution shift. Besides generalization, we also consider adaptation, completely overlooked by previous work, which aims at rapidly fine-tuning these policies to a new test distribution. To tackle both generalization and adaptation issues, we propose ASAP, which decomposes a solver's decision-making into two policies, one for proposal and one for selection. The role of the proposal policy is to suggest promising actions, which allows the selection policy to choose among them. To effectively learn these policies, we introduce a training framework that combines pre-training and post-training, enhanced by meta-learning. During online adaptation, we only fine-tune the selection policy to rapidly adapt to a test distribution. Our experiments demonstrate that ASAP exhibits excellent generalization and adaptation capabilities on in-distribution and out-of-distribution instances for both discrete and continuous setups.

Shilong Deng, Zetao Zheng, Hongcai He et al.

A major challenge in Reinforcement Learning (RL) is the difficulty of learning an optimal policy from sparse rewards. Prior works enhance online RL with conventional Imitation Learning (IL) via a handcrafted auxiliary objective, at the cost of restricting the RL policy to be sub-optimal when the offline data is generated by a non-expert policy. Instead, to better leverage valuable information in offline data, we develop Generalized Imitation Learning from Demonstration (GILD), which meta-learns an objective that distills knowledge from offline data and instills intrinsic motivation towards the optimal policy. Distinct from prior works that are exclusive to a specific RL algorithm, GILD is a flexible module intended for diverse vanilla off-policy RL algorithms. In addition, GILD introduces no domain-specific hyperparameter and minimal increase in computational cost. In four challenging MuJoCo tasks with sparse rewards, we show that three RL algorithms enhanced with GILD significantly outperform state-of-the-art methods.

Zhaohui Jiang, Paul Weng

To improve the sample efficiency of vision-based deep reinforcement learning (RL), we propose a novel method, called SPIRL, to automatically extract important patches from input images. Following Masked Auto-Encoders, SPIRL is based on Vision Transformer models pre-trained in a self-supervised fashion to reconstruct images from randomly-sampled patches. These pre-trained models can then be exploited to detect and select salient patches, defined as hard to reconstruct from neighboring patches. In RL, the SPIRL agent processes selected salient patches via an attention module. We empirically validate SPIRL on Atari games to test its data-efficiency against relevant state-of-the-art methods, including some traditional model-based methods and keypoint-based models. In addition, we analyze our model's interpretability capabilities.

Claire Glanois, Xuening Feng, Zhaohui Jiang et al.

We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems. In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order rules are invented by learning embeddings to match facts and body predicates of a meta-rule. To instantiate it, we specifically design an expressive set of generic meta-rules, and demonstrate they generate a consequent fragment of Horn clauses. During training, we inject a controlled \pw{Gumbel} noise to avoid local optima and employ interpretability-regularization term to further guide the convergence to interpretable rules. We empirically validate our model on various tasks (ILP, visual genome, reinforcement learning) against several state-of-the-art methods.

Claire Glanois, Paul Weng, Matthieu Zimmer et al.

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion. In particular, we argue that interpretable RL may embrace different facets: interpretable inputs, interpretable (transition/reward) models, and interpretable decision-making. Based on this scheme, we summarize and analyze recent work related to interpretable RL with an emphasis on papers published in the past 10 years. We also discuss briefly some related research areas and point to some potential promising research directions.

Wenbin Ouyang, Yisen Wang, Paul Weng et al.

Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. Since training on large instances is impractical, we design a novel deep RL approach with a focus on generalizability. Our proposition consisting of a simple deep learning architecture that learns with novel RL training techniques, exploits two main ideas. First, we exploit equivariance to facilitate training. Second, we interleave efficient local search heuristics with the usual RL training to smooth the value landscape. In order to validate the whole approach, we empirically evaluate our proposition on random and realistic TSP problems against relevant state-of-the-art deep RL methods. Moreover, we present an ablation study to understand the contribution of each of its component

Wenbin Ouyang, Yisen Wang, Shaochen Han et al.

Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In this work, we propose a novel approach named MAGIC that includes a deep learning architecture and a DRL training method. Our architecture, which integrates a multilayer perceptron, a graph neural network, and an attention model, defines a stochastic policy that sequentially generates a TSP solution. Our training method includes several innovations: (1) we interleave DRL policy gradient updates with local search (using a new local search technique), (2) we use a novel simple baseline, and (3) we apply curriculum learning. Finally, we empirically demonstrate that MAGIC is superior to other DRL-based methods on random TSP instances, both in terms of performance and generalizability. Moreover, our method compares favorably against TSP heuristics and other state-of-the-art approach in terms of performance and computational time.

Zhihao Ma, Yuzheng Zhuang, Paul Weng et al.

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning module in a symbolic rule space. The experimental results show that our framework has better interpretability, along with competing performance in comparison to state-of-the-art approaches.

Jianyi Zhang, Paul Weng

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting. Our general model accepts various definitions of safety(e.g., bounds on expected performance, CVaR, variance, or probability of reaching bad states). To ensure safety during learning, we extend a safe policy optimization method to solve our problem. The distributional RL perspective leads to a more efficient algorithm while additionally catering for natural safe constraints. We empirically validate our propositions on artificial and real domains against appropriate state-of-the-art safe RL algorithms.

Matthieu Zimmer, Xuening Feng, Claire Glanois et al.

The integration of reasoning, learning, and decision-making is key to build more general artificial intelligence systems. As a step in this direction, we propose a novel neural-logic architecture, called differentiable logic machine (DLM), that can solve both inductive logic programming (ILP) and reinforcement learning (RL) problems, where the solution can be interpreted as a first-order logic program. Our proposition includes several innovations. Firstly, our architecture defines a restricted but expressive continuous relaxation of the space of first-order logic programs by assigning weights to predicates instead of rules, in contrast to most previous neural-logic approaches. Secondly, with this differentiable architecture, we propose several (supervised and RL) training procedures, based on gradient descent, which can recover a fully-interpretable solution (i.e., logic formula). Thirdly, to accelerate RL training, we also design a novel critic architecture that enables actor-critic algorithms. Fourthly, to solve hard problems, we propose an incremental training procedure that can learn a logic program progressively. Compared to state-of-the-art (SOTA) differentiable ILP methods, DLM successfully solves all the considered ILP problems with a higher percentage of successful seeds (up to 3.5$\times$). On RL problems, without requiring an interpretable solution, DLM outperforms other non-interpretable neural-logic RL approaches in terms of rewards (up to 3.9%). When enforcing interpretability, DLM can solve harder RL problems (e.g., Sorting, Path) Moreover, we show that deep logic programs can be learned via incremental supervised training. In addition to this excellent performance, DLM can scale well in terms of memory and computational time, especially during the testing phase where it can deal with much more constants ($>$2$\times$) than SOTA.

Ruibin Bai, Xinan Chen, Zhi-Long Chen et al.

The Vehicle Routing Problem (VRP) is one of the most intensively studied combinatorial optimisation problems for which numerous models and algorithms have been proposed. To tackle the complexities, uncertainties and dynamics involved in real-world VRP applications, Machine Learning (ML) methods have been used in combination with analytical approaches to enhance problem formulations and algorithmic performance across different problem solving scenarios. However, the relevant papers are scattered in several traditional research fields with very different, sometimes confusing, terminologies. This paper presents a first, comprehensive review of hybrid methods that combine analytical techniques with ML tools in addressing VRP problems. Specifically, we review the emerging research streams on ML-assisted VRP modelling and ML-assisted VRP optimisation. We conclude that ML can be beneficial in enhancing VRP modelling, and improving the performance of algorithms for both online and offline VRP optimisations. Finally, challenges and future opportunities of VRP research are discussed.

Matthieu Zimmer, Claire Glanois, Umer Siddique et al.

We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can accommodate any (sub)differentiable welfare function. Therefore, it is compatible with various notions of fairness that have been proposed in the literature (e.g., lexicographic maximin, generalized Gini social welfare function, proportional fairness). Our solution method is generic and can be implemented in various MARL settings: centralized training and decentralized execution, or fully decentralized. Finally, we experimentally validate our approach in various domains and show that it can perform much better than previous methods.

Jiancong Huang, Juan Rojas, Matthieu Zimmer et al.

Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments. Fixing them incorrectly may negatively impact optimization performance leading notably to insufficient or redundant learning. Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources. The effects are further exacerbated when using single policies to solve multi-task learning problems. Observing that the Evidence Lower Bound (ELBO) used in Variational Auto-Encoders correlates with the diversity of image samples, we propose an auto-tuning technique based on the ELBO for self-supervised reinforcement learning. Our approach can auto-tune three hyperparameters: the replay buffer size, the number of policy gradient updates during each epoch, and the number of exploration steps during each epoch. We use a state-of-the-art self-supervised robot learning framework (Reinforcement Learning with Imagined Goals (RIG) using Soft Actor-Critic) as baseline for experimental verification. Experiments show that our method can auto-tune online and yields the best performance at a fraction of the time and computational resources. Code, video, and appendix for simulated and real-robot experiments can be found at the project page \url{www.JuanRojas.net/autotune}.

Umer Siddique, Paul Weng, Matthieu Zimmer

As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the problem of learning a policy that treats its users equitably. In this paper, we formulate this novel RL problem, in which an objective function, which encodes a notion of fairness that we formally define, is optimized. For this problem, we provide a theoretical discussion where we examine the case of discounted rewards and that of average rewards. During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward. Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward. Thus, we describe how several classic deep RL algorithms can be adapted to our fair optimization problem, and we validate our approach with extensive experiments in three different domains.

Olivier Buffet, Olivier Pietquin, Paul Weng

Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making problem where, at every time step, it observes its state, performs an action, receives a reward and moves to a new state. An RL agent learns by trial and error a good policy (or controller) based on observations and numeric reward feedback on the previously performed action. In this chapter, we present the basic framework of RL and recall the two main families of approaches that have been developed to learn a good policy. The first one, which is value-based, consists in estimating the value of an optimal policy, value from which a policy can be recovered, while the other, called policy search, directly works in a policy space. Actor-critic methods can be seen as a policy search technique where the policy value that is learned guides the policy improvement. Besides, we give an overview of some extensions of the standard RL framework, notably when risk-averse behavior needs to be taken into account or when rewards are not available or not known.

Yijiong Lin, Jiancong Huang, Matthieu Zimmer et al.

Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.

Yijiong Lin, Jiancong Huang, Matthieu Zimmer et al.

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries present in robotic tasks. Intuitively, symmetries from observed trajectories define transformations that leave the space of feasible RL trajectories invariant and can be used to generate new feasible trajectories, which could be used for training. Based on this data augmentation idea, we formulate a general framework, called Invariant Transform Experience Replay that we present with two techniques: (i) Kaleidoscope Experience Replay exploits reflectional symmetries and (ii) Goal-augmented Experience Replay which takes advantage of lax goal definitions. In the Fetch tasks from OpenAI Gym, our experimental results show significant increases in learning rates and success rates. Particularly, we attain a 13, 3, and 5 times speedup in the pushing, sliding, and pick-and-place tasks respectively in the multi-goal setting. Performance gains are also observed in similar tasks with obstacles and we successfully deployed a trained policy on a real Baxter robot. Our work demonstrates that invariant transformations on RL trajectories are a promising methodology to speed up learning in deep RL.

Paul Weng

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which could lead to completely unfair outcomes for some users or stakeholders. To tackle this issue, we advocate for the use of social welfare functions that encode fairness and present this general novel problem in the context of (deep) reinforcement learning, although it could possibly be extended to other machine learning tasks.

Matthieu Zimmer, Paul Weng

In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC). This approach is based on a policy update different from that of deterministic policy gradient (DPG). Previous work has observed its excellent performance empirically, but a theoretical justification is lacking. To fill this gap, we provide a theoretical explanation to motivate this unorthodox policy update by relating it to another update and making explicit the objective function of the latter. We furthermore discuss in depth the properties of these updates to get a deeper understanding of the overall approach. In addition, we extend it and propose a new trust region algorithm, Penalized NFAC (PeNFAC). Finally, we experimentally demonstrate in several classic control problems that it surpasses the state-of-the-art algorithms to learn deterministic policies.

Qitian Wu, Hengrui Zhang, Xiaofeng Gao et al.

Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and under the forms of constant weights or fixed constraints. To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention weight and the other is modeled by a dynamic and context-aware attention weight. We also extend the social effects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that different social effects in two domains could interact with each other and jointly influence user preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social effects. Experiments on one benchmark dataset and a commercial dataset verify the efficacy of the key components in our model. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods.

Robert Busa-Fekete, Balazs Szorenyi, Paul Weng et al.

We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized. The goal of the agent is to find a policy, which can optimize these objectives simultaneously in a fair way. This multi-objective online optimization problem is formalized by using the Generalized Gini Index (GGI) aggregation function. We propose an online gradient descent algorithm which exploits the convexity of the GGI aggregation function, and controls the exploration in a careful way achieving a distribution-free regret $\tilde{\bigO} (T^{-1/2} )$ with high probability. We test our algorithm on synthetic data as well as on an electric battery control problem where the goal is to trade off the use of the different cells of a battery in order to balance their respective degradation rates.

Paul Weng

In this paper, we present a link between preference-based and multiobjective sequential decision-making. While transforming a multiobjective problem to a preference-based one is quite natural, the other direction is a bit less obvious. We present how this transformation (from preference-based to multiobjective) can be done under the classic condition that preferences over histories can be represented by additively decomposable utilities and that the decision criterion to evaluate policies in a state is based on expectation. This link yields a new source of multiobjective sequential decision-making problems (i.e., when reward values are unknown) and justifies the use of solving methods developed in one setting in the other one.

Dajian Li, Paul Weng, Orkun Karabasoglu

In this paper, we tackle the problem of risk-averse route planning in a transportation network with time-dependent and stochastic costs. To solve this problem, we propose an adaptation of the A* algorithm that accommodates any risk measure or decision criterion that is monotonic with first-order stochastic dominance. We also present a case study of our algorithm on the Manhattan, NYC, transportation network.

Hugo Gilbert, Paul Weng, Yan Xu

In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile criterion. Both finite and infinite horizons are considered. Finally we experimentally evaluate our approach on random MDPs and on a data center control problem.

Hugo Gilbert, Paul Weng

In reinforcement learning, the standard criterion to evaluate policies in a state is the expectation of (discounted) sum of rewards. However, this criterion may not always be suitable, we consider an alternative criterion based on the notion of quantiles. In the case of episodic reinforcement learning problems, we propose an algorithm based on stochastic approximation with two timescales. We evaluate our proposition on a simple model of the TV show, Who wants to be a millionaire.

Patrice Perny, Paul Weng, Judy Goldsmith et al.

This paper is devoted to fair optimization in Multiobjective Markov Decision Processes (MOMDPs). A MOMDP is an extension of the MDP model for planning under uncertainty while trying to optimize several reward functions simultaneously. This applies to multiagent problems when rewards define individual utility functions, or in multicriteria problems when rewards refer to different features. In this setting, we study the determination of policies leading to Lorenz-non-dominated tradeoffs. Lorenz dominance is a refinement of Pareto dominance that was introduced in Social Choice for the measurement of inequalities. In this paper, we introduce methods to efficiently approximate the sets of Lorenz-non-dominated solutions of infinite-horizon, discounted MOMDPs. The approximations are polynomial-sized subsets of those solutions.

Paul Weng

The aim of this paper is to propose a generalization of previous approaches in qualitative decision making. Our work is based on the binary possibilistic utility (PU), which is a possibilistic counterpart of Expected Utility (EU).We first provide a new axiomatization of PU and study its relation with the lexicographic aggregation of pessimistic and optimistic utilities. Then we explain the reasons of the coarseness of qualitative decision criteria. Finally, thanks to a redefinition of possibilistic lotteries and mixtures, we present the refined binary possibilistic utility, which is more discriminating than previously proposed criteria.

Paul Weng

Expected Utility: Algebraic Expected Utility In this paper, we provide two axiomatizations of algebraic expected utility, which is a particular generalized expected utility, in a von Neumann-Morgenstern setting, i.e. uncertainty representation is supposed to be given and here to be described by a plausibility measure valued on a semiring, which could be partially ordered. We show that axioms identical to those for expected utility entail that preferences are represented by an algebraic expected utility. This algebraic approach allows many previous propositions (expected utility, binary possibilistic utility,...) to be unified in a same general framework and proves that the obtained utility enjoys the same nice features as expected utility: linearity, dynamic consistency, autoduality of the underlying uncertainty measure, autoduality of the decision criterion and possibility of modeling decision maker's attitude toward uncertainty.