Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments
Authors:
- Hongyi ChenHCHongyi Chen
- Changliu LiuCLChangliu Liu
Preprint
Abstract
This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with limited samples. To guarantee safety in real-world complex environments, we use the safe set algorithm (SSA) to monitor and modify the nominal controls, and evaluate SSA+RL in a clustered dynamic environment which is challenging to be solved by existing RL algorithms. However, the SSA+RL framework is usually not sample-efficient especially in reward-sparse environments, which has not been addressed in previous safe RL works. To improve the learning efficiency, we propose three techniques: (1) avoiding behaving overly conservative by adapting the SSA; (2) encouraging safe exploration using random network distillation with safety constraints; (3) improving policy convergence by treating SSA as expert demonstrations and directly learn from that. The experimental results show that our framework can achieve better safety performance compare to other safe RL methods during training and solve the task with substantially fewer episodes. Project website: https://hychen-naza.github.io/projects/Safe_RL/.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function2021
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysisMachine Learning, 2021
- Cautious Reinforcement Learning with Logical Constraints2020
- Learning on real robots from experience and simple user feedbackJournal of Physical Agents (JoPha), 2013
- Autonomous Helicopter Aerobatics through Apprenticeship LearningThe International Journal of Robotics Research, 2010
- Risk-Sensitive Reinforcement Learning Applied to Control under ConstraintsJournal of Artificial Intelligence Research, 2005