paper-with-me

Papers

Information-Theoretic Considerations in Batch Reinforcement Learning

2019-05-01 · Jinglin Chen, Nan Jiang

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution shift, and (2) representation conditions that are stronger than realizability. However, the necessity ("why do we need them?") and the naturalness ("when do they hold?") of such assumptions have largely eluded the literature. In this paper, we revisit these assumptions and provide theoretical results towards answering the above questions, and make steps towards a deeper understanding of value-function approximation.

📄 PDF Abstract BibTeX arXiv:1905.00360

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Automated Reinforcement Learning: An Overview

2022-01-13 · Reza Refaei Afshar, Yingqian Zhang, Joaquin Vanschoren, Uzay Kaymak

Reinforcement Learning and recently Deep Reinforcement Learning are popular methods for solving sequential decision making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms …

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+2

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

2020-12-14 · Andrea Zanette

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy o…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms

2019-10-21 · ICML 2020 1 · Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou 외

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising…

Reinforcement Learning

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning

2024-08-05 · Seyeon Kim, Joonhun Lee, Namhoon Cho, Sungjun Han 외

Conventional uncertainty-aware temporal difference (TD) learning often assumes a zero-mean Gaussian distribution for TD errors, leading to inaccurate error representations and compromised uncertainty estimation. We intro…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+1

On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency

2022-03-03 · Thanh Nguyen-Tang

This thesis rigorously studies fundamental reinforcement learning (RL) methods in modern practical considerations, including robust RL, distributional RL, and offline RL with neural function approximation. The thesis fir…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)