Shimon Whiteson

is this you? claim profile

∙ 1 follower
University of Oxford ∙ University of Alberta ∙ University of Amsterdam

Professor in the Department of Computer Science at the University of Oxford, Fellow of St Catherine's College, Chief Scientist at Morpheus Labs, Associate Professor at University of Amsterdam from 2007-2015

Breaking the Deadly Triad with a Target Network

The deadly triad refers to the instability of a reinforcement learning a...
01/21/2021 ∙ by Shangtong Zhang, et al. ∙ 0 ∙ share

read it
Deep Interactive Bayesian Reinforcement Learning via Meta-Learning

Agents that interact with other agents often do not know a priori what t...
01/11/2021 ∙ by Luisa Zintgraf, et al. ∙ 0 ∙ share

read it
Average-Reward Off-Policy Policy Evaluation with Function Approximation

We consider off-policy policy evaluation with function approximation (FA...
01/08/2021 ∙ by Shangtong Zhang, et al. ∙ 0 ∙ share

read it
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

This paper focuses on cooperative value-based multi-agent reinforcement ...
10/06/2020 ∙ by Tarun Gupta, et al. ∙ 4 ∙ share

read it
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...
10/05/2020 ∙ by Vitaly Kurin, et al. ∙ 7 ∙ share

read it
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

We investigate the discounting mismatch in actor-critic algorithm implem...
10/02/2020 ∙ by Shangtong Zhang, et al. ∙ 1 ∙ share

read it
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning

Meta-learning is a powerful tool for learning policies that can adapt ef...
10/02/2020 ∙ by Luisa Zintgraf, et al. ∙ 4 ∙ share

read it
Exploiting Submodular Value Functions For Scaling Up Active Perception

In active perception tasks, an agent aims to select sensory actions that...
09/21/2020 ∙ by Yash Satsangi, et al. ∙ 5 ∙ share

read it
WordCraft: An Environment for Benchmarking Commonsense Agents

The ability to quickly solve a wide range of real-world tasks requires a...
07/17/2020 ∙ by Minqi Jiang, et al. ∙ 17 ∙ share

read it
Learning Retrospective Knowledge with Reverse Reinforcement Learning

We present a Reverse Reinforcement Learning (Reverse RL) approach for re...
07/09/2020 ∙ by Shangtong Zhang, et al. ∙ 25 ∙ share

read it
Weighted QMIX: Expanding Monotonic Value Function Factorisation

QMIX is a popular Q-learning algorithm for cooperative MARL in the centr...
06/18/2020 ∙ by Tabish Rashid, et al. ∙ 0 ∙ share

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

Non-stationarity arises in Reinforcement Learning (RL) even in stationar...
06/10/2020 ∙ by Maximilian Igl, et al. ∙ 13 ∙ share

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

Real world multi-agent tasks often involve varying types and quantities ...
06/07/2020 ∙ by Shariq Iqbal, et al. ∙ 9 ∙ share

read it
Privileged Information Dropout in Reinforcement Learning

Using privileged information during training can improve the sample effi...
05/19/2020 ∙ by Pierre-Alexandre Kamienny, et al. ∙ 14 ∙ share

read it
Maximizing Information Gain in Partially Observable Environments via Prediction Reward

Information gathering in a partially observable environment can be formu...
05/11/2020 ∙ by Yash Satsangi, et al. ∙ 32 ∙ share

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

We present a new per-step reward perspective for risk-averse control in ...
04/22/2020 ∙ by Shangtong Zhang, et al. ∙ 15 ∙ share

read it
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

In many real-world settings, a team of agents must coordinate its behavi...
03/19/2020 ∙ by Tabish Rashid, et al. ∙ 1 ∙ share

read it
Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control

Deep multi-agent reinforcement learning (MARL) holds the promise of auto...
03/14/2020 ∙ by Christian Schroeder de Witt, et al. ∙ 13 ∙ share

read it
Optimistic Exploration even with a Pessimistic Initialisation

Optimistic initialisation is an effective strategy for efficient explora...
02/26/2020 ∙ by Tabish Rashid, et al. ∙ 5 ∙ share

read it
Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Quantum hardware and quantum-inspired algorithms are becoming increasing...
02/11/2020 ∙ by Dmitrii Beloborodov, et al. ∙ 23 ∙ share

read it
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

We present GradientDICE for estimating the density ratio between the sta...
01/29/2020 ∙ by Shangtong Zhang, et al. ∙ 51 ∙ share

read it
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...
01/23/2020 ∙ by Guangliang Li, et al. ∙ 0 ∙ share

read it
VIABLE: Fast Adaptation via Backpropagating Learned Loss

In few-shot learning, typically, the loss function which is applied at t...
11/29/2019 ∙ by Leo Feng, et al. ∙ 10 ∙ share

read it
Provably Convergent Off-Policy Actor-Critic with Function Approximation

We present the first provably convergent off-policy actor-critic algorit...
11/11/2019 ∙ by Shangtong Zhang, et al. ∙ 26 ∙ share

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

Trading off exploration and exploitation in an unknown environment is ke...
10/18/2019 ∙ by Luisa Zintgraf, et al. ∙ 66 ∙ share

read it
MAVEN: Multi-Agent Variational Exploration

Centralised training with decentralised execution is an important settin...
10/16/2019 ∙ by Anuj Mahajan, et al. ∙ 17 ∙ share

read it
Deep Coordination Graphs

This paper introduces the deep coordination graph (DCG) for collaborativ...
09/27/2019 ∙ by Wendelin Böhmer, et al. ∙ 54 ∙ share

read it
Improving SAT Solver Heuristics with Graph Networks and Reinforcement Learning

We present GQSAT, a branching heuristic in a Boolean SAT solver trained ...
09/26/2019 ∙ by Vitaly Kurin, et al. ∙ 37 ∙ share

read it
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...
09/23/2019 ∙ by Gregory Farquhar, et al. ∙ 20 ∙ share

read it
Growing Action Spaces

In complex tasks, such as those with large combinatorial action spaces, ...
06/28/2019 ∙ by Gregory Farquhar, et al. ∙ 7 ∙ share

read it
A Survey of Reinforcement Learning Informed by Natural Language

To be successful in real-world tasks, Reinforcement Learning (RL) needs ...
06/10/2019 ∙ by Jelena Luketina, et al. ∙ 52 ∙ share

read it
Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning

This paper investigates the use of intrinsic reward to guide exploration...
06/05/2019 ∙ by Wendelin Böhmer, et al. ∙ 14 ∙ share

read it
Deep Residual Reinforcement Learning

We revisit residual algorithms in both model-free and model-based reinfo...
05/03/2019 ∙ by Shangtong Zhang, et al. ∙ 38 ∙ share

read it
DAC: The Double Actor-Critic Architecture for Learning Options

We reformulate the option framework as two parallel augmented MDPs. Unde...
04/29/2019 ∙ by Shangtong Zhang, et al. ∙ 16 ∙ share

read it
Multitask Soft Option Learning

We present Multitask Soft Option Learning (MSOL), a hierarchical multita...
04/01/2019 ∙ by Maximilian Igl, et al. ∙ 98 ∙ share

read it
Generalized Off-Policy Actor-Critic

We propose a new objective, the counterfactual objective, unifying exist...
03/27/2019 ∙ by Shangtong Zhang, et al. ∙ 28 ∙ share

read it
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Recent years have seen the application of deep reinforcement learning te...
02/20/2019 ∙ by Jacopo Castellini, et al. ∙ 0 ∙ share

read it
Fast Efficient Hyperparameter Tuning for Policy Gradients

The performance of policy gradient methods is sensitive to hyperparamete...
02/18/2019 ∙ by Supratik Paul, et al. ∙ 20 ∙ share

read it
The StarCraft Multi-Agent Challenge

In the last few years, deep multi-agent reinforcement learning (RL) has ...
02/11/2019 ∙ by Mikayel Samvelyan, et al. ∙ 32 ∙ share

read it
Stable Opponent Shaping in Differentiable Games

A growing number of learning methods are actually games which optimise m...
11/20/2018 ∙ by Alistair Letcher, et al. ∙ 74 ∙ share

read it
Learning from Demonstration in the Wild

Learning from demonstration (LfD) is useful in settings where hand-codin...
11/08/2018 ∙ by Feryal Behbahani, et al. ∙ 8 ∙ share

read it
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning

When observing the actions of others, humans carry out inferences about ...
11/04/2018 ∙ by Jakob N. Foerster, et al. ∙ 0 ∙ share

read it
VIREL: A Variational Inference Framework for Reinforcement Learning

Applying probabilistic models to reinforcement learning (RL) has become ...
11/03/2018 ∙ by Matthew Fellows, et al. ∙ 0 ∙ share

read it
Multi-Agent Common Knowledge Reinforcement Learning

In multi-agent reinforcement learning, centralised policies can only be ...
10/27/2018 ∙ by Jakob N. Foerster, et al. ∙ 0 ∙ share

read it
CAML: Fast Context Adaptation via Meta-Learning

We propose CAML, a meta-learning method for fast adaptation that partiti...
10/08/2018 ∙ by Luisa M Zintgraf, et al. ∙ 2 ∙ share

read it
Deep Variational Reinforcement Learning for POMDPs

Many real-world sequential decision making problems are partially observ...
06/06/2018 ∙ by Maximilian Igl, et al. ∙ 2 ∙ share

read it
Contextual Policy Optimisation

Policy gradient methods have been successfully applied to a variety of r...
05/27/2018 ∙ by Supratik Paul, et al. ∙ 2 ∙ share

read it
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

In many real-world settings, a team of agents must coordinate their beha...
03/30/2018 ∙ by Tabish Rashid, et al. ∙ 0 ∙ share

read it
TACO: Learning Task Decomposition via Temporal Alignment for Control

Many advanced Learning from Demonstration (LfD) methods consider the dec...
03/02/2018 ∙ by Kyriacos Shiarlis, et al. ∙ 0 ∙ share

read it
Fourier Policy Gradients

We propose a new way of deriving policy gradient updates for reinforceme...
02/19/2018 ∙ by Matthew Fellows, et al. ∙ 0 ∙ share

read it

Shimon Whiteson

Featured Co-authors