paper-with-me

홈 › Papers

Off-Policy Reinforcement Learning with High Dimensional Reward

2024-08-14 · Dong Neuck Lee, Michael R. Kosorok

Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a Euclidean space, leading to highly flexible choices for utility. This paper establishes robust theoretical foundations for DRL. We prove the contraction property of the Bellman operator even when the reward space is an infinite-dimensional separable Banach space. Furthermore, we demonstrate that the behavior of high- or infinite-dimensional returns can be effectively approximated using a lower-dimensional Euclidean space. Leveraging these theoretical insights, we propose a novel DRL algorithm that tackles problems which have been previously intractable using conventional reinforcement learning approaches.

📄 PDF Abstract BibTeX arXiv:2408.07660

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Reinforcement Learning without Ground-Truth State

2019-05-20 · Xingyu Lin, Harjatin Singh Baweja, David Held

To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Manipulation

Learning Intrinsic Symbolic Rewards in Reinforcement Learning

2020-10-08 · Hassam Sheikh, Shauharda Khadka, Santiago Miret, Somdeb Majumdar

Learning effective policies for sparse objectives is a key challenge in Deep Reinforcement Learning (RL). A common approach is to design task-related dense rewards to improve task learnability. While such rewards are eas…

Deep Reinforcement LearningMuJoCoreinforcement-learningReinforcement Learning+1

On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory

2024-10-10 · Yangchun Zhang, Wang Zhou, Yirui Zhou

In the context of inverse reinforcement learning (IRL) with a single expert, adversarial inverse reinforcement learning (AIRL) serves as a foundational approach to providing comprehensive and transferable task descriptio…

reinforcement-learningReinforcement Learning

Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks

2023-10-16 · Zihao Li, Xiang Ji, Minshuo Chen, Mengdi Wang

A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, …

Off-policy evaluationreinforcement-learning

Reward prediction for representation learning and reward shaping

2021-05-07 · Hlynur Davíð Hlynsson, Laurenz Wiskott

One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments w…

PredictionReinforcement Learning (RL)Representation Learning