paper-with-me

Papers

Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning

2021-01-23 · William F. Whitney, Michael Bloesch, Jost Tobias Springenberg, Abbas Abdolmaleki, Kyunghyun Cho, Martin Riedmiller

Despite the close connection between exploration and sample efficiency, most state of the art reinforcement learning algorithms include no considerations for exploration beyond maximizing the entropy of the policy. In this work we address this seeming missed opportunity. We observe that the most common formulation of directed exploration in deep RL, known as bonus-based exploration (BBE), suffers from bias and slow coverage in the few-sample regime. This causes BBE to be actively detrimental to policy learning in many control tasks. We show that by decoupling the task policy from the exploration policy, directed exploration can be highly effective for sample-efficient continuous control. Our method, Decoupled Exploration and Exploitation Policies (DEEP), can be combined with any off-policy RL algorithm without modification. When used in conjunction with soft actor-critic, DEEP incurs no performance penalty in densely-rewarding environments. On sparse environments, DEEP gives a several-fold improvement in data efficiency due to better exploration.

📄 PDF Abstract BibTeX arXiv:2101.09458

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration

2021-07-19 · ICML Workshop URL 2021 7 · Lukas Schäfer, Filippos Christianos, Josiah P. Hanna, Stefano V. Albrecht

Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work,…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL

2026-02-13 · Yixiao Zhou, Yang Li, Dongzhou Cheng, Hehe Fan 외 arxiv

Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather than a purely inference-time choice. Sampl…

Hierarchical Reinforcement LearningMathematical Reasoning

A Provably Efficient Sample Collection Strategy for Reinforcement Learning

2020-07-13 · NeurIPS 2021 12 · Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric

One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for re…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

2022-12-14 · Linrui Zhang, Zichen Yan, Li Shen, Shoujie Li 외

Learning a risk-aware policy is essential but rather challenging in unstructured robotic tasks. Safe reinforcement learning methods open up new possibilities to tackle this problem. However, the conservative policy updat…

reinforcement-learningReinforcement Learning (RL)Safe Reinforcement Learning

Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias

2023-10-12 · Max Sobol Mark, Archit Sharma, Fahim Tajwar, Rafael Rafailov 외

It is desirable for policies to optimistically explore new states and behaviors during online reinforcement learning (RL) or fine-tuning, especially when prior offline data does not provide enough state coverage. However…

D4RLOffline RLOpenAI GymReinforcement Learning (RL)