paper-with-me

Papers

Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse

2022-06-28 · James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras

We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the efficiency of sample reuse, addressing a trade-off between two important deployment requirements for real-world control: (i) practical performance guarantees and (ii) data efficiency. We demonstrate the benefits of this new class of algorithms through extensive experimental analysis on a broad range of simulated control tasks.

📄 PDF Abstract BibTeX arXiv:2206.13714

Code (2)

jqueeney/gpi 공식 구현 tf
jqueeney/geppo tf

Tasks

Continuous ControlDecision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Generalized Proximal Policy Optimization with Sample Reuse

2021-10-29 · NeurIPS 2021 12 · James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout train…

Decision Making

Generalized Nested Rollout Policy Adaptation

2020-03-22 · Tristan Cazenave

Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm for single player games. In this paper we propose to generalize NRPA with a temperature and a bias and to analyze theoretically the algorithms. Th…

Traveling Salesman Problem

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

2025-03-23 · Juntao Dai, Taiye Chen, Yaodong Yang, Qian Zheng 외

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies b…

Reinforcement Learning (RL)Response Generation

Non-stationary and Varying-discounting Markov Decision Processes for Reinforcement Learning

2025-11-17 · Zhizuo Chen, Theodore T. Allen arxiv

Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address th…

Reinforcement Learning

Safe Policy Improvement with an Estimated Baseline Policy

2019-09-11 · Thiago D. Simão, Romain Laroche, Rémi Tachet des Combes

Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: repro…

ManagementReinforcement Learning