Safe and Sample-Efficient Reinforcement Learning for Clustered Dynamic Environments
- 17 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 6, 1928-1933
Abstract
This letter 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.Keywords
All Related Versions
This publication has 9 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
- Safe Off-policy Reinforcement Learning Using Barrier Functions2020
- Safe Control Algorithms Using Energy Functions: A Uni ed Framework, Benchmark, and New Directions2019
- End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control TasksProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Control in a Safe Set: Addressing Safety in Human-Robot Interactions2014
- 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
- Consideration of Risk in Reinforcement Learning1994