Search Results for author:
Found 55 papers, 25 papers with code
Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems
The rapidly changing architecture and functionality of electrical networks and the increasing penetration of renewable and distributed energy resources have resulted in various technological and managerial challenges.
LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots
We introduce LLM-Personalize, a novel framework with an optimization pipeline designed to personalize LLM planners for household robotics.
Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras
To overcome these hardware constraints, we propose Multi-View Disentanglement (MVD), which uses multiple cameras to learn a policy that achieves zero-shot generalisation to any single camera from the training set.
Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review
One way to mitigate this challenge is to utilize explainable AI (XAI) techniques.
ICED: Zero-Shot Transfer in Reinforcement Learning via In-Context Environment Design
ICED generates levels using a variational autoencoder trained over an initial set of level parameters, reducing distributional shift, and achieves significant improvements in ZSG over adaptive level sampling strategies and UED methods.
Sample Relationship from Learning Dynamics Matters for Generalisation
Although much research has been done on proposing new models or loss functions to improve the generalisation of artificial neural networks (ANNs), less attention has been directed to the impact of the training data on generalisation.
Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning
Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning.
Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning
Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process.
How the level sampling process impacts zero-shot generalisation in deep reinforcement learning
A key limitation preventing the wider adoption of autonomous agents trained via deep reinforcement learning (RL) is their limited ability to generalise to new environments, even when these share similar characteristics with environments encountered during training.
Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes.
SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
The Starcraft Multi-Agent Challenge (SMAC) has been widely used in MARL research, but is built on top of a heavy, closed-source computer game, StarCraft II.
Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments
Motivated by the recent success of Offline RL and Imitation Learning (IL), we conduct a study to investigate whether agents can leverage offline data in the form of trajectories to improve the sample-efficiency in procedurally generated environments.
Revisiting the Gumbel-Softmax in MADDPG
This method, however, is statistically biased, and a recent MARL benchmarking paper suggests that this bias makes MADDPG perform poorly in grid-world situations, where the action space is discrete.
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
We present CEMA: Causal Explanations in Multi-Agent systems; a framework for creating causal natural language explanations of an agent's decisions in dynamic sequential multi-agent systems to build more trustworthy autonomous agents.
Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition
Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
In this work, we propose ensemble value functions for multi-agent exploration (EMAX), a general framework to seamlessly extend value-based MARL algorithms with ensembles of value functions.
Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers
We envision a warehouse in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse.
Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles.
A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning
These belief estimates are combined with our solution for the fully observable case to compute an agent's optimal policy under partial observability in open ad hoc teamwork.
Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning
This work focuses on equilibrium selection in no-conflict multi-agent games, where we specifically study the problem of selecting a Pareto-optimal Nash equilibrium among several existing equilibria.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Deep Reinforcement Learning for Multi-Agent Interaction
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning.
Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity
Early approaches address the AHT challenge by training the learner with a diverse set of handcrafted teammate policies, usually designed based on an expert's domain knowledge about the policies the learner may encounter.
Few-Shot Teamwork
We propose the novel few-shot teamwork (FST) problem, where skilled agents trained in a team to complete one task are combined with skilled agents from different tasks, and together must learn to adapt to an unseen but related task.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training.
Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning
We show that a team of agents is able to adapt to novel tasks when provided with task embeddings.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Verifiable Goal Recognition for Autonomous Driving with Occlusions
Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour.
Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning
Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined.
A Survey of Ad Hoc Teamwork Research
Ad hoc teamwork is the research problem of designing agents that can collaborate with new teammates without prior coordination.
Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning
Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy.
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens.
Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration
Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters.
Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability
Researchers are using deep learning models to explore the emergence of language in various language games, where agents interact and develop an emergent language to solve tasks.
GRIT: Fast, Interpretable, and Verifiable Goal Recognition with Learned Decision Trees for Autonomous Driving
As autonomous driving is safety-critical, it is important to have methods which are human interpretable and for which safety can be formally verified.
Autonomous Driving
Robotics
Multiagent Systems
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
In this paper, we present PILOT -- a planning framework that comprises an imitation neural network followed by an efficient optimiser that actively rectifies the network's plan, guaranteeing fulfilment of safety and comfort requirements.
Towards Quantum-Secure Authentication and Key Agreement via Abstract Multi-Agent Interaction
Authentication and key agreement are decided based on the agents' observed behaviors during the interaction.
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including joint training.
Agent Modelling under Partial Observability for Deep Reinforcement Learning
Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution.
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult.
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards.
Integrating Planning and Interpretable Goal Recognition for Autonomous Driving
The ability to predict the intentions and driving trajectories of other vehicles is a key problem for autonomous driving.
Robotics
Variational Autoencoders for Opponent Modeling in Multi-Agent Systems
Modeling the behavior of other agents (opponents) is essential in understanding the interactions of the agents in the system.
Stabilizing Generative Adversarial Networks: A Survey
Generative Adversarial Networks (GANs) are a type of generative model which have received much attention due to their ability to model complex real-world data.
E-HBA: Using Action Policies for Expert Advice and Agent Typification
Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behaviour of other agents.
Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems
In this work, we empirically evaluate five MAL algorithms, representing major approaches to multiagent learning but originally developed with the homogeneous setting in mind, to understand their behaviour in a set of ad hoc team problems.
On Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems
In this paper, we provide theoretical guidance on two central design parameters of this method: Firstly, it is important that the user choose a posterior which can learn the true distribution of latent types, as otherwise suboptimal actions may be chosen.
Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)
Belief filtering in DBNs is the task of inferring the belief state (i. e. the probability distribution over process states) based on incomplete and uncertain observations.
An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types
To address this problem, researchers have studied learning algorithms which compute posterior beliefs over a hypothesised set of policies, based on the observed actions of the other agents.
Are You Doing What I Think You Are Doing? Criticising Uncertain Agent Models
The key for effective interaction in many multiagent applications is to reason explicitly about the behaviour of other agents, in the form of a hypothesised behaviour.
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains.
Reasoning about Unforeseen Possibilities During Policy Learning
Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning.
Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
Much research in artificial intelligence is concerned with the development of autonomous agents that can interact effectively with other agents.
Belief and Truth in Hypothesised Behaviours
The idea is to hypothesise a set of types, each specifying a possible behaviour for the other agents, and to plan our own actions with respect to those types which we believe are most likely, given the observed actions of the agents.
A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systems
Based on this model, we derive a solution, called Harsanyi-Bellman Ad Hoc Coordination (HBA), which utilises the concept of Bayesian Nash equilibrium in a planning procedure to find optimal actions in the sense of Bellman optimal control.
Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks
Furthermore, we demonstrate how passivity occurs naturally in a complex system such as a multi-robot warehouse, and how PSBF can exploit this to accelerate the filtering task.
