paper-with-me

Papers

Model-based Reinforcement Learning with Ensembled Model-value Expansion

2021-09-29 · Gaurav Manek, J Zico Kolter

Model-based reinforcement learning (MBRL) methods are often more data-efficient and quicker to converge than their model-free counterparts, but typically rely crucially on accurate modeling of the environment dynamics and associated uncertainty in order to perform well. Recent approaches have used ensembles of dynamics models within MBRL to separately capture aleatoric and epistemic uncertainty of the learned dynamics, but many MBRL algorithms are still limited because they treat these dynamics models as a "black box" without fully exploiting the uncertainty modeling. In this paper, we propose a simple but effective approach to improving the performance of MBRL by directly incorporating the ensemble prediction \emph{into} the RL method itself: we propose constructing multiple value roll-outs using different members of the dynamics ensemble, and aggregating the separate estimates to form a joint estimate of the state value. Despite its simplicity, we show that this method substantially improves the performance of MBRL methods: we comprehensively evaluate this technique on common locomotion benchmarks, with ablative experiments to show the added value of our proposed components.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

modelModel-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer

2025-02-04 · Yaodong Yang, Guangyong Chen, Hongyao Tang, Furui Liu 외

Overestimation in single-agent reinforcement learning has been extensively studied. In contrast, overestimation in the multiagent setting has received comparatively little attention although it increases with the number …

Q-LearningSMACSMAC+

Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning

2023-03-07 · Daniel Palenicek, Michael Lutter, Joao Carvalho, Jan Peters

Model-based reinforcement learning is one approach to increase sample efficiency. However, the accuracy of the dynamics model and the resulting compounding error over modelled trajectories are commonly regarded as key li…

continuous-controlContinuous ControlModel-based Reinforcement Learningreinforcement-learning+1

Revisiting Model-based Value Expansion

2022-03-28 · Daniel Palenicek, Michael Lutter, Jan Peters

Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the effectiveness of value function learning. However, to date, these methods are being outperformed by Dyna-styl…

GPUmodelModel-based Reinforcement Learning

Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble

2024-01-30 · Shun Zhang, Zhenfang Chen, Sunli Chen, Yikang Shen 외

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human p…

Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning

Diminishing Return of Value Expansion Methods

2024-12-29 · Daniel Palenicek, Michael Lutter, João Carvalho, Daniel Dennert 외

Model-based reinforcement learning aims to increase sample efficiency, but the accuracy of dynamics models and the resulting compounding errors are often seen as key limitations. This paper empirically investigates poten…

Model-based Reinforcement Learningreinforcement-learningReinforcement Learning