Shimon Whiteson

research

∙ 06/26/2022

Generalized Beliefs for Cooperative AI

Self-play is a common paradigm for constructing solutions in Markov game...

Darius Muglich, et al. ∙

research

∙ 05/06/2022

Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation

Simulation is a crucial tool for accelerating the development of autonom...

Maximilian Igl, et al. ∙

research

∙ 01/31/2022

Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO

We present a new monotonic improvement guarantee for optimizing decentra...

Mingfei Sun, et al. ∙

research

∙ 01/31/2022

You May Not Need Ratio Clipping in PPO

Proximal Policy Optimization (PPO) methods learn a policy by iteratively...

Mingfei Sun, et al. ∙

research

∙ 01/11/2022

In Defense of the Unitary Scalarization for Deep Multi-Task Learning

Recent multi-task learning research argues against unitary scalarization...

Vitaly Kurin, et al. ∙

research

∙ 12/11/2021

Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency

Sample efficiency is crucial for imitation learning methods to be applic...

Mingfei Sun, et al. ∙

research

∙ 12/01/2021

On the Practical Consistency of Meta-Reinforcement Learning Algorithms

Consistency is the theoretical property of a meta learning algorithm tha...

Zheng Xiong, et al. ∙

research

∙ 10/27/2021

Reinforcement Learning in Factored Action Spaces using Tensor Decompositions

We present an extended abstract for the previously published work TESSER...

Anuj Mahajan, et al. ∙

research

∙ 10/27/2021

Model based Multi-agent Reinforcement Learning with Tensor Decompositions

A challenge in multi-agent reinforcement learning is to be able to gener...

Pascal Van Der Vaart, et al. ∙

research

∙ 08/11/2021

Truncated Emphatic Temporal Difference Methods for Prediction and Control

Emphatic Temporal Difference (TD) methods are a class of off-policy Rein...

Shangtong Zhang, et al. ∙

research

∙ 07/17/2021

Implicit Communication as Minimum Entropy Coupling

In many common-payoff games, achieving good performance requires players...

Samuel Sokota, et al. ∙

research

∙ 06/09/2021

Bayesian Bellman Operators

We introduce a novel perspective on Bayesian reinforcement learning (RL)...

Matthew Fellows, et al. ∙

research

∙ 06/06/2021

SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching

We present SoftDICE, which achieves state-of-the-art performance for imi...

Mingfei Sun, et al. ∙

research

∙ 05/31/2021

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Reinforcement Learning in large action spaces is a challenging problem. ...

Anuj Mahajan, et al. ∙

research

∙ 03/22/2021

Regularized Softmax Deep Multi-Agent Q-Learning

Tackling overestimation in Q-learning is an important problem that has b...

Ling Pan, et al. ∙

research

∙ 03/01/2021

Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing

Recent research has shown that Graph Neural Networks (GNNs) can learn po...

Charlie Blake, et al. ∙

research

∙ 01/21/2021

Breaking the Deadly Triad with a Target Network

The deadly triad refers to the instability of a reinforcement learning a...

Shangtong Zhang, et al. ∙

research

∙ 01/11/2021

Deep Interactive Bayesian Reinforcement Learning via Meta-Learning

Agents that interact with other agents often do not know a priori what t...

Luisa Zintgraf, et al. ∙

research

∙ 01/08/2021

Average-Reward Off-Policy Policy Evaluation with Function Approximation

We consider off-policy policy evaluation with function approximation (FA...

Shangtong Zhang, et al. ∙

research

∙ 10/06/2020

UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

This paper focuses on cooperative value-based multi-agent reinforcement ...

Tarun Gupta, et al. ∙

research

∙ 10/05/2020

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Multitask Reinforcement Learning is a promising way to obtain models wit...

Vitaly Kurin, et al. ∙

research

∙ 10/02/2020

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

We investigate the discounting mismatch in actor-critic algorithm implem...

Shangtong Zhang, et al. ∙

research

∙ 10/02/2020

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning

Meta-learning is a powerful tool for learning policies that can adapt ef...

Luisa Zintgraf, et al. ∙

research

∙ 09/21/2020

Exploiting Submodular Value Functions For Scaling Up Active Perception

In active perception tasks, an agent aims to select sensory actions that...

Yash Satsangi, et al. ∙

research

∙ 07/17/2020

WordCraft: An Environment for Benchmarking Commonsense Agents

The ability to quickly solve a wide range of real-world tasks requires a...

Minqi Jiang, et al. ∙

research

∙ 07/09/2020

Learning Retrospective Knowledge with Reverse Reinforcement Learning

We present a Reverse Reinforcement Learning (Reverse RL) approach for re...

Shangtong Zhang, et al. ∙

research

∙ 06/18/2020

Weighted QMIX: Expanding Monotonic Value Function Factorisation

QMIX is a popular Q-learning algorithm for cooperative MARL in the centr...

Tabish Rashid, et al. ∙

research

∙ 06/10/2020

The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning

Non-stationarity arises in Reinforcement Learning (RL) even in stationar...

Maximilian Igl, et al. ∙

research

∙ 06/07/2020

AI-QMIX: Attention and Imagination for Dynamic Multi-Agent Reinforcement Learning

Real world multi-agent tasks often involve varying types and quantities ...

Shariq Iqbal, et al. ∙

research

∙ 05/19/2020

Privileged Information Dropout in Reinforcement Learning

Using privileged information during training can improve the sample effi...

Pierre-Alexandre Kamienny, et al. ∙

research

∙ 05/11/2020

Maximizing Information Gain in Partially Observable Environments via Prediction Reward

Information gathering in a partially observable environment can be formu...

Yash Satsangi, et al. ∙

research

∙ 04/22/2020

Per-Step Reward: A New Perspective for Risk-Averse Reinforcement Learning

We present a new per-step reward perspective for risk-averse control in ...

Shangtong Zhang, et al. ∙

research

∙ 03/19/2020

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

In many real-world settings, a team of agents must coordinate its behavi...

Tabish Rashid, et al. ∙

research

∙ 03/14/2020

Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control

Deep multi-agent reinforcement learning (MARL) holds the promise of auto...

Christian Schroeder de Witt, et al. ∙

research

∙ 02/26/2020

Optimistic Exploration even with a Pessimistic Initialisation

Optimistic initialisation is an effective strategy for efficient explora...

Tabish Rashid, et al. ∙

research

∙ 02/11/2020

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Quantum hardware and quantum-inspired algorithms are becoming increasing...

Dmitrii Beloborodov, et al. ∙

research

∙ 01/29/2020

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

We present GradientDICE for estimating the density ratio between the sta...

Shangtong Zhang, et al. ∙

research

∙ 01/23/2020

Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework

Interactive reinforcement learning provides a way for agents to learn to...

Guangliang Li, et al. ∙

research

∙ 11/29/2019

VIABLE: Fast Adaptation via Backpropagating Learned Loss

In few-shot learning, typically, the loss function which is applied at t...

Leo Feng, et al. ∙

research

∙ 11/11/2019

Provably Convergent Off-Policy Actor-Critic with Function Approximation

We present the first provably convergent off-policy actor-critic algorit...

Shangtong Zhang, et al. ∙

research

∙ 10/18/2019

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning

Trading off exploration and exploitation in an unknown environment is ke...

Luisa Zintgraf, et al. ∙

research

∙ 10/16/2019

MAVEN: Multi-Agent Variational Exploration

Centralised training with decentralised execution is an important settin...

Anuj Mahajan, et al. ∙

research

∙ 09/27/2019

Deep Coordination Graphs

This paper introduces the deep coordination graph (DCG) for collaborativ...

Wendelin Böhmer, et al. ∙

research

∙ 09/26/2019

Improving SAT Solver Heuristics with Graph Networks and Reinforcement Learning

We present GQSAT, a branching heuristic in a Boolean SAT solver trained ...

Vitaly Kurin, et al. ∙

research

∙ 09/23/2019

Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning

Gradient-based methods for optimisation of objectives in stochastic sett...

Gregory Farquhar, et al. ∙

research

∙ 06/28/2019

Growing Action Spaces

In complex tasks, such as those with large combinatorial action spaces, ...

Gregory Farquhar, et al. ∙

research

∙ 06/10/2019

A Survey of Reinforcement Learning Informed by Natural Language

To be successful in real-world tasks, Reinforcement Learning (RL) needs ...

Jelena Luketina, et al. ∙

research

∙ 06/05/2019

Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning

This paper investigates the use of intrinsic reward to guide exploration...

Wendelin Böhmer, et al. ∙

research

∙ 05/03/2019

Deep Residual Reinforcement Learning

We revisit residual algorithms in both model-free and model-based reinfo...

Shangtong Zhang, et al. ∙

research

∙ 04/29/2019

DAC: The Double Actor-Critic Architecture for Learning Options

We reformulate the option framework as two parallel augmented MDPs. Unde...

Shangtong Zhang, et al. ∙

Shimon Whiteson

Featured Co-authors