Francisco Cruz

Adrian Ly, Richard Dazeley, Peter Vamplew et al.

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the $Q$-values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon ($n$), and our empirical experiments show that a poorly chosen static value for $n$ can in many cases lead to worse performance than single-step DQN. Inspired by the success of $n$-step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call `Elastic Step DQN' (ES-DQN). It dynamically varies the step size horizon in multi-step updates based on the similarity of states visited. Our empirical evaluation shows that ES-DQN out-performs $n$-step with fixed $n$ updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias.

Francisco Cruz, Charlotte Young, Richard Dazeley et al.

Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations.

Niclas Schroeter, Francisco Cruz, Stefan Wermter

With the increasing presence of robotic systems and human-robot environments in today's society, understanding the reasoning behind actions taken by a robot is becoming more important. To increase this understanding, users are provided with explanations as to why a specific action was taken. Among other effects, these explanations improve the trust of users in their robotic partners. One option for creating these explanations is an introspection-based approach which can be used in conjunction with reinforcement learning agents to provide probabilities of success. These can in turn be used to reason about the actions taken by the agent in a human-understandable fashion. In this work, this introspection-based approach is developed and evaluated further on the basis of an episodic and a non-episodic robotics simulation task. Furthermore, an additional normalization step to the Q-values is proposed, which enables the usage of the introspection-based approach on negative and comparatively small Q-values. Results obtained show the viability of introspection for episodic robotics tasks and, additionally, that the introspection-based approach can be used to generate explanations for the actions taken in a non-episodic robotics environment as well.

Jasmin Bernotat, Doreen Jirak, Eduardo Benitez Sandoval et al.

We present a research outline that aims at investigating group dynamics and peer pressure in the context of industrial robots. Our research plan was motivated by the fact that industrial robots became already an integral part of human-robot co-working. However, industrial robots have been sparsely integrated into research on robot credibility, group dynamics, and potential users' tendency to follow a robot's indication. Therefore, we aim to transfer the classic Asch experiment (see \cite{Asch_51}) into HRI with industrial robots. More precisely, we will test to what extent participants follow a robot's response when confronted with a group (vs. individual) industrial robot arms (vs. human) peers who give a false response. We are interested in highlighting the effects of group size, perceived robot credibility, psychological stress, and peer pressure in the context of industrial robots. With the results of this research, we hope to highlight group dynamics that might underlie HRI in industrial settings in which numerous robots already work closely together with humans in shared environments.

Francisco Cruz, Adam Bignold, Hung Son Nguyen et al.

The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Moreover, the information provided by each interaction is not retained and instead discarded by the agent after a single use. In this paper, we present a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Results obtained show that the use of broad-persistent advice substantially improves the performance of the agent while reducing the number of interactions required for the trainer.

Angel Ayala, Donling Sui, Francisco Cruz et al.

Autonomous Unmanned Aerial Vehicles (UAVs) have revolutionized industries through their versatility with applications including aerial surveillance, search and rescue, agriculture, and delivery. Their autonomous capabilities offer unique advantages, such as operating in large open space environments. Reinforcement Learning (RL) empowers UAVs to learn intricate navigation policies, enabling them to optimize flight behavior autonomously. However, one of its main challenge is the inefficiency in using data sample to achieve a good policy. In object-goal navigation (OGN) settings, target recognition arises as an extra challenge. Most UAV-related approaches use relative or absolute coordinates to move from an initial position to a predefined location, rather than to find the target directly. This study addresses the data sample efficiency issue in solving a 3D OGN problem, in addition to, the formalization of the unknown target location setting as a Markov decision process. Experiments are conducted to analyze the interplay of different state representation learning (SRL) methods for perception with a model-free RL algorithm for planning in an autonomous navigation system. The main contribution of this study is the development of the perception module, featuring a novel self-predictive model named AmelPred. Empirical results demonstrate that its stochastic version, AmelPredSto, is the best-performing SRL model when combined with actor-critic RL algorithms. The obtained results show substantial improvement in RL algorithms' efficiency by using AmelPredSto in solving the OGN problem.

Cristian Millán-Arias, Ruben Contreras, Francisco Cruz et al.

In recent years, unmanned aerial vehicle (UAV) related technology has expanded knowledge in the area, bringing to light new problems and challenges that require solutions. Furthermore, because the technology allows processes usually carried out by people to be automated, it is in great demand in industrial sectors. The automation of these vehicles has been addressed in the literature, applying different machine learning strategies. Reinforcement learning (RL) is an automation framework that is frequently used to train autonomous agents. RL is a machine learning paradigm wherein an agent interacts with an environment to solve a given task. However, learning autonomously can be time consuming, computationally expensive, and may not be practical in highly-complex scenarios. Interactive reinforcement learning allows an external trainer to provide advice to an agent while it is learning a task. In this study, we set out to teach an RL agent to control a drone using reward-shaping and policy-shaping techniques simultaneously. Two simulated scenarios were proposed for the training; one without obstacles and one with obstacles. We also studied the influence of each technique. The results show that an agent trained simultaneously with both techniques obtains a lower reward than an agent trained using only a policy-based approach. Nevertheless, the agent achieves lower execution times and less dispersion during training.

Hugo Muñoz, Ernesto Portugal, Angel Ayala et al.

Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem occurs when reinforcement learning is used in critical contexts where the users of the system need to have more information and reliability for the actions executed by an agent. In this regard, explainable reinforcement learning seeks to provide to an agent in training with methods in order to explain its behavior in such a way that users with no experience in machine learning could understand the agent's behavior. One of these is the memory-based explainable reinforcement learning method that is used to compute probabilities of success for each state-action pair using an episodic memory. In this work, we propose to make use of the memory-based explainable reinforcement learning method in a hierarchical environment composed of sub-tasks that need to be first addressed to solve a more complex task. The end goal is to verify if it is possible to provide to the agent the ability to explain its actions in the global task as well as in the sub-tasks. The results obtained showed that it is possible to use the memory-based method in hierarchical environments with high-level tasks and compute the probabilities of success to be used as a basis for explaining the agent's behavior.

Maryam Hashemi, Ali Darejeh, Francisco Cruz

The increasing complexity of AI systems has led to the growth of the field of Explainable Artificial Intelligence (XAI), which aims to provide explanations and justifications for the outputs of AI algorithms. While there is considerable demand for XAI, there remains a scarcity of studies aimed at comprehensively understanding the practical distinctions among different methods and effectively aligning each method with users individual needs, and ideally, offer a mapping function which can map each user with its specific needs to a method of explainability. This study endeavors to bridge this gap by conducting a thorough review of extant research in XAI, with a specific focus on Explainable Machine Learning (XML), and a keen eye on user needs. Our main objective is to offer a classification of XAI methods within the realm of XML, categorizing current works into three distinct domains: philosophy, theory, and practice, and providing a critical review for each category. Moreover, our study seeks to facilitate the connection between XAI users and the most suitable methods for them and tailor explanations to meet their specific needs by proposing a mapping function that take to account users and their desired properties and suggest an XAI method to them. This entails an examination of prevalent XAI approaches and an evaluation of their properties. The primary outcome of this study is the formulation of a clear and concise strategy for selecting the optimal XAI method to achieve a given goal, all while delivering personalized explanations tailored to individual users.

Philipp Schoenegger, Francesco Salvi, Jiacheng Liu et al. · oxford

We directly compare the persuasion capabilities of a frontier large language model (LLM; Claude Sonnet 3.5) against incentivized human persuaders in an interactive, real-time conversational quiz setting. In this preregistered, large-scale incentivized experiment, participants (quiz takers) completed an online quiz where persuaders (either humans or LLMs) attempted to persuade quiz takers toward correct or incorrect answers. We find that LLM persuaders achieved significantly higher compliance with their directional persuasion attempts than incentivized human persuaders, demonstrating superior persuasive capabilities in both truthful (toward correct answers) and deceptive (toward incorrect answers) contexts. We also find that LLM persuaders significantly increased quiz takers' accuracy, leading to higher earnings, when steering quiz takers toward correct answers, and significantly decreased their accuracy, leading to lower earnings, when steering them toward incorrect answers. Overall, our findings suggest that AI's persuasion capabilities already exceed those of humans that have real-money bonuses tied to performance. Our findings of increasingly capable AI persuaders thus underscore the urgency of emerging alignment and governance frameworks.

Haopeng Zhao, Marsha Mariya Kappan, Mahdi Bamdad et al.

Human pose estimation is a crucial task in computer vision. Methods that have SOTA (State-of-the-Art) accuracy, often involve a large number of parameters and incur substantial computational cost. Many lightweight variants have been proposed to reduce the model size and computational cost of them. However, several of these methods still contain components that are not well suited for efficient deployment on edge devices. Moreover, models that primarily emphasize inference speed on edge devices often suffer from limited accuracy due to their overly simplified designs. To address these limitations, we propose LAPX, an Hourglass network with self-attention that captures global contextual information, based on previous work, LAP. In addition to adopting the self-attention module, LAPX advances the stage design and refine the lightweight attention modules. It achieves competitive results on two benchmark datasets, MPII and COCO, with only 2.3M parameters, and demonstrates real-time performance, confirming its edge-device suitability.

Hadassah Harland, Richard Dazeley, Peter Vamplew et al.

Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs and values. We contribute to this pursuit with a dynamic approach for aligning AI with diverse and shifting user preferences through Multi Objective Reinforcement Learning (MORL), via post-learning policy selection adjustment. In this paper, we introduce the proposed framework for this approach, outline its anticipated advantages and assumptions, and discuss technical details about the implementation. We also examine the broader implications of adopting a retroactive alignment approach through the sociotechnical systems perspective.

Abdulrahman Althobaiti, Angel Ayala, JingYing Gao et al.

Large Language Models (LLMs) are transforming the robotics domain by enabling robots to comprehend and execute natural language instructions. The cornerstone benefits of LLM include processing textual data from technical manuals, instructions, academic papers, and user queries based on the knowledge provided. However, deploying LLM-generated code in robotic systems without safety verification poses significant risks. This paper outlines a safety layer that verifies the code generated by ChatGPT before executing it to control a drone in a simulated environment. The safety layer consists of a fine-tuned GPT-4o model using Few-Shot learning, supported by knowledge graph prompting (KGP). Our approach improves the safety and compliance of robotic actions, ensuring that they adhere to the regulations of drone operations.

M. Oltan Sevinc, Liao Wu, Francisco Cruz

Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios.

Maher Mesto, Francisco Cruz

Interactive reinforcement learning (IRL) has shown promise in enabling autonomous agents and robots to learn complex behaviours from human teachers, yet the dynamics of teacher selection remain poorly understood. This paper reveals an unexpected phenomenon in IRL: when given a choice between teachers with different reward structures, learning agents overwhelmingly prefer conservative, low-reward teachers (93.16% selection rate) over those offering 20x higher rewards. Through 1,250 experimental runs in navigation tasks with multiple expert teachers, we discovered: (1) Conservative bias dominates teacher selection: agents systematically choose the lowest-reward teacher, prioritising consistency over optimality; (2) Critical performance thresholds exist at teacher availability rho >= 0.6 and accuracy omega >= 0.6, below which the framework fails catastrophically; (3) The framework achieves 159% improvement over baseline Q-learning under concept drift. These findings challenge fundamental assumptions about optimal teaching in RL and suggest potential implications for human-robot collaboration, where human preferences for safety and consistency may align with the observed agent selection behaviour, potentially informing training paradigms for safety-critical robotic applications.

Marsha Mariya Kappan, Eduardo Benitez Sandoval, Erik Meijering et al.

Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have complex architecture. Here we propose a lightweight attention based pose estimation network that utilizes depthwise separable convolution and Convolutional Block Attention Module on an hourglass backbone. The network significantly reduces the computational complexity (floating point operations) and the model size (number of parameters) containing only about 10% of parameters of original eight stack Hourglass network. Experiments were conducted on COCO and MPII datasets using a two stack hourglass backbone. The results showed that our model performs well in comparison to six other lightweight pose estimation models with an average precision of 72.07. The model achieves this performance with only 2.3M parameters and 3.7G FLOPs.

Zihan Lin, Francisco Cruz, Eduardo Benitez Sandoval

Emotion recognition plays a crucial role in various domains of human-robot interaction. In long-term interactions with humans, robots need to respond continuously and accurately, however, the mainstream emotion recognition methods mostly focus on short-term emotion recognition, disregarding the context in which emotions are perceived. Humans consider that contextual information and different contexts can lead to completely different emotional expressions. In this paper, we introduce self context-aware model (SCAM) that employs a two-dimensional emotion coordinate system for anchoring and re-labeling distinct emotions. Simultaneously, it incorporates its distinctive information retention structure and contextual loss. This approach has yielded significant improvements across audio, video, and multimodal. In the auditory modality, there has been a notable enhancement in accuracy, rising from 63.10% to 72.46%. Similarly, the visual modality has demonstrated improved accuracy, increasing from 77.03% to 80.82%. In the multimodal, accuracy has experienced an elevation from 77.48% to 78.93%. In the future, we will validate the reliability and usability of SCAM on robots through psychology experiments.

Hung Son Nguyen, Francisco Cruz, Richard Dazeley

Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for a revisit. In this paper, we present Broad-persistent Advising (BPA), a broad-persistent advising approach that retains and reuses the processed information. It not only helps trainers to give more general advice relevant to similar states instead of only the current state but also allows the agent to speed up the learning process. We test the proposed approach in two continuous robotic scenarios, namely, a cart pole balancing task and a simulated robot navigation task. The obtained results show that the performance of the agent using BPA improves while keeping the number of interactions required for the trainer in comparison to the DeepIRL approach.

Richard Dazeley, Peter Vamplew, Francisco Cruz

Broad Explainable Artificial Intelligence moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent's behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms all operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) is relatively recent field of research that aims to develop techniques to extract concepts from the agent's: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce a conceptual framework, called the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. Additionally, we recognise that RL methods have the ability to incorporate a range of technologies to allow agents to adapt to their environment. CXF is designed for the incorporation of many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes and justify its decisions.

Angel Ayala, Francisco Cruz, Bruno Fernandes et al.

Explainable reinforcement learning allows artificial agents to explain their behavior in a human-like manner aiming at non-expert end-users. An efficient alternative of creating explanations is to use an introspection-based method that transforms Q-values into probabilities of success used as the base to explain the agent's decision-making process. This approach has been effectively used in episodic and discrete scenarios, however, to compute the probability of success in non-episodic and more complex environments has not been addressed yet. In this work, we adapt the introspection method to be used in a non-episodic task and try it in a continuous Atari game scenario solved with the Rainbow algorithm. Our initial results show that the probability of success can be computed directly from the Q-values for all possible actions.

Cristian Millán-Arias, Bruno Fernandes, Francisco Cruz

Proxemics is a branch of non-verbal communication concerned with studying the spatial behavior of people and animals. This behavior is an essential part of the communication process due to delimit the acceptable distance to interact with another being. With increasing research on human-agent interaction, new alternatives are needed that allow optimal communication, avoiding agents feeling uncomfortable. Several works consider proxemic behavior with cognitive agents, where human-robot interaction techniques and machine learning are implemented. However, environments consider fixed personal space and that the agent previously knows it. In this work, we aim to study how agents behave in environments based on proxemic behavior, and propose a modified gridworld to that aim. This environment considers an issuer with proxemic behavior that provides a disagreement signal to the agent. Our results show that the learning agent can identify the proxemic space when the issuer gives feedback about agent performance.

Richard Dazeley, Peter Vamplew, Cameron Foale et al.

Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers for this growth include recent legislative changes and increased investments by industry and governments, along with increased concern from the general public. People are affected by autonomous decisions every day and the public need to understand the decision-making process to accept the outcomes. However, the vast majority of the applications of XAI/IML are focused on providing low-level `narrow' explanations of how an individual decision was reached based on a particular datum. While important, these explanations rarely provide insights into an agent's: beliefs and motivations; hypotheses of other (human, animal or AI) agents' intentions; interpretation of external cultural expectations; or, processes used to generate its own explanation. Yet all of these factors, we propose, are essential to providing the explanatory depth that people require to accept and trust the AI's decision-making. This paper aims to define levels of explanation and describe how they can be integrated to create a human-aligned conversational explanation system. In so doing, this paper will survey current approaches and discuss the integration of different technologies to achieve these levels with Broad eXplainable Artificial Intelligence (Broad-XAI), and thereby move towards high-level `strong' explanations.

Adam Bignold, Francisco Cruz, Richard Dazeley et al.

Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Additionally, the information provided by each interaction is not retained and instead discarded by the agent after a single-use. In this work, we propose a persistent rule-based interactive reinforcement learning approach, i.e., a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Our experimental results show persistent advice substantially improves the performance of the agent while reducing the number of interactions required for the trainer. Moreover, rule-based advice shows similar performance impact as state-based advice, but with a substantially reduced interaction count.

Adam Bignold, Francisco Cruz, Richard Dazeley et al.

Interactive reinforcement learning proposes the use of externally-sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has focused on the effect of human-sourced advice by including real-time feedback on the interactive reinforcement learning process, specifically aiming to improve the learning speed of the agent, while minimising the time demands on the human. This work focuses on answering which of two approaches, evaluative or informative, is the preferred instructional approach for humans. Moreover, this work presents an experimental setup for a human-trial designed to compare the methods people use to deliver advice in terms of human engagement. The results obtained show that users giving informative advice to the learner agents provide more accurate advice, are willing to assist the learner agent for a longer time, and provide more advice per episode. Additionally, self-evaluation from participants using the informative approach has indicated that the agent's ability to follow the advice is higher, and therefore, they feel their own advice to be of higher accuracy when compared to people providing evaluative advice.

Ruben Contreras, Angel Ayala, Francisco Cruz

Currently, unmanned aerial vehicles, such as drones, are becoming a part of our lives and reaching out to many areas of society, including the industrialized world. A common alternative to control the movements and actions of the drone is through unwired tactile interfaces, for which different remote control devices can be found. However, control through such devices is not a natural, human-like communication interface, which sometimes is difficult to master for some users. In this work, we present a domain-based speech recognition architecture to effectively control an unmanned aerial vehicle such as a drone. The drone control is performed using a more natural, human-like way to communicate the instructions. Moreover, we implement an algorithm for command interpretation using both Spanish and English languages, as well as to control the movements of the drone in a simulated domestic environment. The conducted experiments involve participants giving voice commands to the drone in both languages in order to compare the effectiveness of each of them, considering the mother tongue of the participants in the experiment. Additionally, different levels of distortion have been applied to the voice commands in order to test the proposed approach when facing noisy input signals. The obtained results show that the unmanned aerial vehicle is capable of interpreting user voice instructions achieving an improvement in speech-to-action recognition for both languages when using phoneme matching in comparison to only using the cloud-based algorithm without domain-based instructions. Using raw audio inputs, the cloud-based approach achieves 74.81% and 97.04% accuracy for English and Spanish instructions respectively, whereas using our phoneme matching approach the results are improved achieving 93.33% and 100.00% accuracy for English and Spanish languages.

Angel Ayala, Bruno Fernandes, Francisco Cruz et al.

Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71\% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.

Angel Ayala, Francisco Cruz, Diego Campos et al.

Research on humanoid robotic systems involves a considerable amount of computational resources, not only for the involved design but also for its development and subsequent implementation. For robotic systems to be implemented in real-world scenarios, in several situations, it is preferred to develop and test them under controlled environments in order to reduce the risk of errors and unexpected behavior. In this regard, a more accessible and efficient alternative is to implement the environment using robotic simulation tools. This paper presents a quantitative comparison of Gazebo, Webots, and V-REP, three simulators widely used by the research community to develop robotic systems. To compare the performance of these three simulators, elements such as CPU, memory footprint, and disk access are used to measure and compare them to each other. In order to measure the use of resources, each simulator executes 20 times a robotic scenario composed by a NAO robot that must navigate to a goal position avoiding a specific obstacle. In general terms, our results show that Webots is the simulator with the lowest use of resources, followed by V-REP, which has advantages over Gazebo, mainly because of the CPU use.

Pablo Barros, Ana Tanevska, Francisco Cruz et al.

Designing the decision-making processes of artificial agents that are involved in competitive interactions is a challenging task. In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, do not show the temporal-relation between the selected actions. We address this problem by proposing the \emph{Moody framework}. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how our model allows the agents' to obtain a holistic representation of the competitive dynamics within the game.

Ithan Moreira, Javier Rivas, Francisco Cruz et al.

Robots are extending their presence in domestic environments every day, being more common to see them carrying out tasks in home scenarios. In the future, robots are expected to increasingly perform more complex tasks and, therefore, be able to acquire experience from different sources as quickly as possible. A plausible approach to address this issue is interactive feedback, where a trainer advises a learner on which actions should be taken from specific states to speed up the learning process. Moreover, deep reinforcement learning has been recently widely utilized in robotics to learn the environment and acquire new skills autonomously. However, an open issue when using deep reinforcement learning is the excessive time needed to learn a task from raw input images. In this work, we propose a deep reinforcement learning approach with interactive feedback to learn a domestic task in a human-robot scenario. We compare three different learning methods using a simulated robotic arm for the task of organizing different objects; the proposed methods are (i) deep reinforcement learning (DeepRL); (ii) interactive deep reinforcement learning using a previously trained artificial agent as an advisor (agent-IDeepRL); and (iii) interactive deep reinforcement learning using a human advisor (human-IDeepRL). We demonstrate that interactive approaches provide advantages for the learning process. The obtained results show that a learner agent, using either agent-IDeepRL or human-IDeepRL, completes the given task earlier and has fewer mistakes compared to the autonomous DeepRL approach.

Adam Bignold, Francisco Cruz, Matthew E. Taylor et al.

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent's performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems.

Francisco Cruz, Richard Dazeley, Peter Vamplew et al.

Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot's actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent's observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson's correlation and the mean squared error.

Nikhil Churamani, Francisco Cruz, Sascha Griffiths et al.

The purpose of the present study is to learn emotion expression representations for artificial agents using reward shaping mechanisms. The approach takes inspiration from the TAMER framework for training a Multilayer Perceptron (MLP) to learn to express different emotions on the iCub robot in a human-robot interaction scenario. The robot uses a combination of a Convolutional Neural Network (CNN) and a Self-Organising Map (SOM) to recognise an emotion and then learns to express the same using the MLP. The objective is to teach a robot to respond adequately to the user's perception of emotions and learn how to express different emotions.

Francisco Cruz, Sven Magg, Yukie Nagai et al.

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which uses a parent-like trainer to propose the next action to be performed and by doing so reduces the search space by advice. On some occasions, the trainer may be another artificial agent which in turn was trained using reinforcement learning methods to afterward becoming an advisor for other learner-agents. In this work, we analyze internal representations and characteristics of artificial agents to determine which agent may outperform others to become a better trainer-agent. Using a polymath agent, as compared to a specialist agent, an advisor leads to a larger reward and faster convergence of the reward signal and also to a more stable behavior in terms of the state visit frequency of the learner-agents. Moreover, we analyze system interaction parameters in order to determine how influential they are in the apprenticeship process, where the consistency of feedback is much more relevant when dealing with different learner obedience parameters.

Francisco Cruz, German I. Parisi, Stefan Wermter

Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in terms of vocal commands and hand gestures as feedback. Our architecture integrates multi-modal information to provide robust commands from multiple sensory cues along with a confidence value indicating the trustworthiness of the feedback. The integration process also considers the case in which the two modalities convey incongruent information. Additionally, we modulate the influence of sensory-driven feedback in the IRL task using goal-oriented knowledge in terms of contextual affordances. We implement a neural network architecture to predict the effect of performed actions with different objects to avoid failed-states, i.e., states from which it is not possible to accomplish the task. In our experimental setup, we explore the interplay of multimodal feedback and task-specific affordances in a robot cleaning scenario. We compare the learning performance of the agent under four different conditions: traditional RL, multi-modal IRL, and each of these two setups with the use of contextual affordances. Our experiments show that the best performance is obtained by using audio-visual feedback with affordancemodulated IRL. The obtained results demonstrate the importance of multi-modal sensory processing integrated with goal-oriented knowledge in IRL tasks.

Francisco Cruz, Oriol Ramos Terrades

We successfully combine Expectation-Maximization algorithm and variational approaches for parameter learning and computing inference on Markov random felds. This is a general method that can be applied to many computer vision tasks. In this paper, we apply it to handwritten text line segmentation. We conduct several experiments that demonstrate that our method deal with common issues of this task, such as complex document layout or non-latin scripts. The obtained results prove that our method achieve state-of-the-art performance on different benchmark datasets without any particular fine tuning step.