Stefano V. Albrecht

research

∙ 07/11/2023

Contextual Pre-Planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning

Recent studies show that deep reinforcement learning (DRL) agents tend t...

0 Guy Azran, et al. ∙

research

∙ 05/23/2023

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

Reinforcement Learning (RL) environments can produce training data with ...

0 Mhairi Dunion, et al. ∙

research

∙ 05/09/2023

SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning

There is a lack of standard benchmarks for Multi-Agent Reinforcement Lea...

0 Adam Michalski, et al. ∙

research

∙ 04/18/2023

Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments

One of the key challenges of Reinforcement Learning (RL) is the ability ...

0 Alain Andres, et al. ∙

research

∙ 02/23/2023

Revisiting the Gumbel-Softmax in MADDPG

MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that...

0 Callum Rhys Tilbury, et al. ∙

research

∙ 02/21/2023

Causal Social Explanations for Stochastic Sequential Multi-Agent Decision-Making

We present a novel framework to generate causal explanations for the dec...

0 Balint Gyevnar, et al. ∙

research

∙ 02/09/2023

Learning Complex Teamwork Tasks using a Sub-task Curriculum

Training a team to complete a complex task via multi-agent reinforcement...

0 Elliot Fosong, et al. ∙

research

∙ 02/07/2023

Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) requires agents to...

13 Lukas Schäfer, et al. ∙

research

∙ 12/22/2022

Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers

This project leverages advances in multi-agent reinforcement learning (M...

0 Aleksandar Krnjaic, et al. ∙

research

∙ 10/26/2022

Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models

Reasoning with occluded traffic agents is a significant open challenge f...

0 Filippos Christianos, et al. ∙

research

∙ 10/12/2022

DiPA: Diverse and Probabilistically Accurate Interactive Prediction

Accurate prediction is important for operating an autonomous vehicle in ...

0 Anthony Knittel, et al. ∙

research

∙ 10/11/2022

A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning

Open ad hoc teamwork is the problem of training a single agent to effici...

0 Arrasy Rahman, et al. ∙

research

∙ 09/28/2022

Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning

Equilibrium selection in multi-agent games refers to the problem of sele...

0 Filippos Christianos, et al. ∙

research

∙ 08/02/2022

Deep Reinforcement Learning for Multi-Agent Interaction

The development of autonomous agents which can interact with other agent...

10 Ibrahim H. Ahmed, et al. ∙

research

∙ 07/29/2022

Perspectives on the System-level Design of a Safe Autonomous Driving Stack

Achieving safe and robust autonomy is the key bottleneck on the path tow...

0 Majd Hawasly, et al. ∙

research

∙ 07/28/2022

Towards Robust Ad Hoc Teamwork Agents By Creating Diverse Training Teammates

Ad hoc teamwork (AHT) is the problem of creating an agent that must coll...

0 Arrasy Rahman, et al. ∙

research

∙ 07/19/2022

Few-Shot Teamwork

We propose the novel few-shot teamwork (FST) problem, where skilled agen...

0 Elliot Fosong, et al. ∙

research

∙ 07/15/2022

Cooperative Marine Operations via Ad Hoc Teams

While research in ad hoc teamwork has great potential for solving real-w...

0 Ignacio Carlucho, et al. ∙

research

∙ 07/12/2022

Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning

In real-world robotics applications, Reinforcement Learning (RL) agents ...

0 Mhairi Dunion, et al. ∙

research

∙ 07/05/2022

Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning

Successful deployment of multi-agent reinforcement learning often requir...

14 Lukas Schäfer, et al. ∙

research

∙ 06/28/2022

Verifiable Goal Recognition for Autonomous Driving with Occlusions

When used in autonomous driving, goal recognition allows the future beha...

0 Cillian Brewitt, et al. ∙

research

∙ 06/22/2022

Learning Representations for Control with Hierarchical Forward Models

Learning control from pixels is difficult for reinforcement learning (RL...

0 Trevor McInroe, et al. ∙

research

∙ 06/17/2022

A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning

Inscrutable AI systems are difficult to trust, especially if they operat...

0 Balint Gyevnar, et al. ∙

research

∙ 05/17/2022

MIDGARD: A Simulation Platform for Autonomous Navigation in Unstructured Environments

We present MIDGARD, an open source simulation platform for autonomous ro...

0 Giuseppe Vecchio, et al. ∙

research

∙ 03/15/2022

Flash: Fast and Light Motion Prediction for Autonomous Driving with Bayesian Inverse Planning and Learned Motion Profiles

Motion prediction of road users in traffic scenes is critical for autono...

0 Morris Antonello, et al. ∙

research

∙ 02/16/2022

A Survey of Ad Hoc Teamwork: Definitions, Methods, and Open Problems

Ad hoc teamwork is the well-established research problem of designing ag...

0 Reuth Mirsky, et al. ∙

research

∙ 11/29/2021

Robust On-Policy Data Collection for Data-Efficient Policy Evaluation

This paper considers how to complement offline reinforcement learning (R...

0 Rujie Zhong, et al. ∙

research

∙ 10/11/2021

Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning

Deep reinforcement learning (RL) agents that exist in high-dimensional s...

0 Trevor McInroe, et al. ∙

research

∙ 08/05/2021

Interpretable Goal Recognition in the Presence of Occluded Factors for Autonomous Vehicles

Recognising the goals or intentions of observed vehicles is a key step t...

0 Josiah P. Hanna, et al. ∙

research

∙ 07/19/2021

Decoupling Exploration and Exploitation in Reinforcement Learning

Intrinsic rewards are commonly applied to improve exploration in reinfor...

14 Lukas Schäfer, et al. ∙

research

∙ 03/10/2021

GRIT: Verifiable Goal Recognition for Autonomous Driving using Decision Trees

It is useful for autonomous vehicles to have the ability to infer the go...

0 Cillian Brewitt, et al. ∙

research

∙ 02/15/2021

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

Sharing parameters in multi-agent deep reinforcement learning has played...

0 Filippos Christianos, et al. ∙

research

∙ 07/18/2020

Quantum-Secure Authentication via Abstract Multi-Agent Interaction

Current methods for authentication based on public-key cryptography are ...

0 Ibrahim Ahmed, et al. ∙

research

∙ 06/18/2020

Open Ad Hoc Teamwork using Graph-based Policy Learning

Ad hoc teamwork is the challenging problem of designing an autonomous ag...

0 Arrasy Rahman, et al. ∙

research

∙ 06/16/2020

Local Information Opponent Modelling Using Variational Autoencoders

Modelling the behaviours of other agents (opponents) is essential for un...

0 Georgios Papoudakis, et al. ∙

research

∙ 06/14/2020

Comparative Evaluation of Multi-Agent Deep Reinforcement Learning Algorithms

Multi-agent deep reinforcement learning (MARL) suffers from a lack of co...

49 Georgios Papoudakis, et al. ∙

research

∙ 06/12/2020

Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning

Exploration in multi-agent reinforcement learning is a challenging probl...

0 Filippos Christianos, et al. ∙

research

∙ 02/06/2020

Integrating Planning and Interpretable Goal Recognition for Autonomous Driving

The ability to predict the intentions and driving trajectories of other ...

0 Stefano V. Albrecht, et al. ∙

research

∙ 02/06/2020

A Two-Stage Optimization Approach to Safe-by-Design Planning for Autonomous Driving

Lessons learned from the increasing diversity of road trial deployments ...

0 Francisco Eiras, et al. ∙

research

∙ 01/29/2020

Variational Autoencoders for Opponent Modeling in Multi-Agent Systems

Multi-agent systems exhibit complex behaviors that emanate from the inte...

0 Georgios Papoudakis, et al. ∙

research

∙ 09/30/2019

Stabilizing Generative Adversarial Network Training: A Survey

Generative Adversarial Networks (GANs) are a type of Generative Models, ...

0 Maciej Wiatrak, et al. ∙

research

∙ 07/23/2019

E-HBA: Using Action Policies for Expert Advice and Agent Typification

Past research has studied two approaches to utilise predefined policy se...

1 Stefano V. Albrecht, et al. ∙

research

∙ 07/22/2019

Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems

This paper is concerned with evaluating different multiagent learning (M...

3 Stefano V. Albrecht, et al. ∙

research

∙ 07/15/2019

On Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems

While many multiagent algorithms are designed for homogeneous systems (i...

0 Stefano V. Albrecht, et al. ∙

research

∙ 07/10/2019

An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types

Many multiagent applications require an agent to learn quickly how to in...

5 Stefano V. Albrecht, et al. ∙

research

∙ 07/10/2019

Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)

Dynamic Bayesian networks (DBNs) are a general model for stochastic proc...

1 Stefano V. Albrecht, et al. ∙

research

∙ 07/02/2019

Are You Doing What I Think You Are Doing? Criticising Uncertain Agent Models

The key for effective interaction in many multiagent applications is to ...

1 Stefano V. Albrecht, et al. ∙

research

∙ 06/26/2019

Reasoning about Hypothetical Agent Behaviours and their Parameters

Agents can achieve effective interaction with previously unknown other a...

0 Stefano V. Albrecht, et al. ∙

research

∙ 06/11/2019

Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning

Recent developments in deep reinforcement learning are concerned with cr...

0 Georgios Papoudakis, et al. ∙

research

∙ 01/10/2018

Reasoning about Unforeseen Possibilities During Policy Learning

Methods for learning optimal policies in autonomous agents often assume ...

0 Craig Innes, et al. ∙

Stefano V. Albrecht

Featured Co-authors