209 citations · 733 across the 29 of their papers we have counts for
29 papers
Visual Imitation Learning with Patch Rewards
Minghuan Liu, Tairan He, Weinan Zhang +2
Visual imitation learning enables reinforcement learning agents to learn to behave from expert visual demonstrations such as videos or image sequences, without explicit, well-defin…
Learning to Optimize for Reinforcement Learning
Qingfeng Lan, A. Rupam Mahmood, Shuicheng Yan +1
In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-d…
Reinforcement Learning from Diverse Human Preferences
Wanqi Xue, Bo An, Shuicheng Yan +1
The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behavio…
RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Wei Qiu, Xiao Ma, Bo An +3
Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios…
Boosting Offline Reinforcement Learning via Data Rebalancing
Yang Yue, Bingyi Kang, Xiao Ma +3
Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on design…
DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physics
Siwei Chen, Yiqing Xu, Cunjun Yu +4
Deformable Object Manipulation (DOM) is of significant importance to both daily and industrial applications. Recent successes in differentiable physics simulators allow learning al…
Mutual Information Regularized Offline Reinforcement Learning
Xiao Ma, Bingyi Kang, Zhongwen Xu +2
The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrap…
Efficient Offline Policy Optimization with a Learned Model
Zichen Liu, Siyi Li, Wee Sun Lee +2
MuZero Unplugged presents a promising approach for offline policy learning from logged data. It conducts Monte-Carlo Tree Search (MCTS) with a learned model and leverages Reanalyze…
Imitation Learning via Differentiable Physics
Siwei Chen, Xiao Ma, Zhongwen Xu
Existing imitation learning (IL) methods such as inverse reinforcement learning (IRL) usually have a double-loop training process, alternating between learning a reward function an…
Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning
Yang Yue, Bingyi Kang, Zhongwen Xu +2
Deep reinforcement learning (RL) algorithms suffer severe performance degradation when the interaction data is scarce, which limits their real-world application. Recently, visual r…
EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine
Jiayi Weng, Min Lin, Shengyi Huang +9
There has been significant progress in developing reinforcement learning (RL) training systems. Past works such as IMPALA, Apex, Seed RL, Sample Factory, and others, aim to improve…
ETA Prediction with Graph Neural Networks in Google Maps
Austin Derrow-Pinion, Jennifer She, David Wong +14
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time…
Emphatic Algorithms for Deep Reinforcement Learning
Ray Jiang, Tom Zahavy, Zhongwen Xu +4
Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms ca…
Discovery of Options via Meta-Learned Subgoals
Vivek Veeriah, Tom Zahavy, Matteo Hessel +6
Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster. However, despite prior work on this topic, the problem of disc…
Balancing Constraints and Rewards with Meta-Gradient D4PG
Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy +4
Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints. Often the constraint thresholds are incorrectly…
Meta-Gradient Reinforcement Learning with an Objective Discovered Online
Zhongwen Xu, Hado van Hasselt, Matteo Hessel +3
Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each a…
Discovering Reinforcement Learning Algorithms
Junhyuk Oh, Matteo Hessel, Wojciech M. Czarnecki +4
Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discov…
A Self-Tuning Actor-Critic Algorithm
Tom Zahavy, Zhongwen Xu, Vivek Veeriah +5
Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well…
What Can Learned Intrinsic Rewards Capture?
Zeyu Zheng, Junhyuk Oh, Matteo Hessel +5
The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and imm…
Discovery of Useful Questions as Auxiliary Tasks
Vivek Veeriah, Matteo Hessel, Zhongwen Xu +6
Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this depart…
General non-linear Bellman equations
Hado van Hasselt, John Quan, Matteo Hessel +3
We consider a general class of non-linear Bellman equations. These open up a design space of algorithms that have interesting properties, which has two potential advantages. First,…
Meta-Gradient Reinforcement Learning
Zhongwen Xu, Hado van Hasselt, David Silver
The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide t…
Finite Element Methods For Wave Propagation With Debye Polarization In Nonlinear Dielectric Materials
Qiumei Huang, Shanghui Jia, Fei Xu +2
In this paper, we consider the wave propagation with Debye polarization in nonlinear dielectric materials. For this model, the Rother's method is employed to derive the well-posedn…
An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
Fan Wu, Zhongwen Xu, Yi Yang
We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i.e., referr…