Safe Exploration Method for Reinforcement Learning under Existence of Disturbance
Not on the map. Why?
Abstract (arXiv)
Recent rapid developments in reinforcement learning algorithms have been giving us novel possibilities in many fields. However, due to their exploring property, we have to take the risk into consideration when we apply those algorithms to safety-critical problems especially in real environments. In this study, we deal with a safe exploration problem in reinforcement learning under the existence of disturbance. We define the safety during learning as satisfaction of the constraint conditions explicitly defined in terms of the state and propose a safe exploration method that uses partial prior knowledge of a controlled object and disturbance. The proposed method assures the satisfaction of the explicit state constraints with a pre-specified probability even if the controlled object is exposed to a stochastic disturbance following a normal distribution. As theoretical results, we introduce sufficient conditions to construct conservative inputs not containing an exploring aspect used in the proposed method and prove that the safety in the above explained sense is guaranteed with the proposed method. Furthermore, we illustrate the validity and effectiveness of the proposed method through numerical simulations of an inverted pendulum and a four-bar parallel link robot manipulator.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 30 Sep 2022.
Builds on
16 of 21 references.
References · 16
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2021Convex optimizationcited by 2,479
- 2017Constrained Policy Optimizationcited by 928
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
- 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
- 2019Control Barrier Functions: Theory and Applicationscited by 332
- 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
- 2020Projection-Based Constrained Policy Optimizationcited by 195
- 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 156
- 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
- 2018Learning-based Model Predictive Control for Safe Explorationcited by 116
- 2019Bayesian Learning-Based Adaptive Control for Safety Critical Systemscited by 19
4 more
- 2019Probabilistic Safety Constraints for Learned High Relative Degree System Dynamicscited by 9
- 2019Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Modelscited by 7
- 2020Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Methodcited by 7
- 2021Automatic Exploration Process Adjustment for Safe Reinforcement Learning with Joint Chance Constraint Satisfactioncited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.