paper-with-me

Papers

Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning

2021-11-25 · Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Wenchao Sun, Jianyu Chen

In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger. This fact causes that the agent cannot learn a zero-violation policy even after convergence. Otherwise, it would not receive any penalty and lose the knowledge about danger. In this paper, we propose the safe set actor-critic (SSAC) algorithm, which confines the policy update using safety-oriented energy functions, or the safety indexes. The safety index is designed to increase rapidly for potentially dangerous actions, which allows us to locate the safe set on the action space, or the control safe set. Therefore, we can identify the dangerous actions prior to taking them, and further obtain a zero constraint-violation policy after convergence.We claim that we can learn the energy function in a model-free manner similar to learning a value function. By using the energy function transition as the constraint objective, we formulate a constrained RL problem. We prove that our Lagrangian-based solutions make sure that the learned policy will converge to the constrained optimum under some assumptions. The proposed algorithm is evaluated on both the complex simulation environments and a hardware-in-loop (HIL) experiment with a real controller from the autonomous vehicle. Experimental results suggest that the converged policy in all environments achieves zero constraint violation and comparable performance with model-based baselines.

📄 PDF Abstract BibTeX arXiv:2111.12953

Code (1)

mahaitongdae/safety_index_synthesis tf

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach

2021-09-13 · Qinbo Bai, Amrit Singh Bedi, Mridul Agarwal, Alec Koppel 외

Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes sa…

Decision Makingreinforcement-learningReinforcement Learning (RL)

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm

2022-06-12 · Qinbo Bai, Amrit Singh Bedi, Vaneet Aggarwal

We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conser…

Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs

2021-06-04 · NeurIPS 2021 12 · Tao Liu, Ruida Zhou, Dileep Kalathil, P. R. Kumar 외

We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret …

Safe Exploration

Extreme Value Policy Optimization for Safe Reinforcement Learning

2026-01-17 · Shiqing Gao, Yihang Zhou, Shuai Shao, Haoyu Luo 외 arxiv

Ensuring safety is a critical challenge in applying Reinforcement Learning (RL) to real-world scenarios. Constrained Reinforcement Learning (CRL) addresses this by maximizing returns under predefined constraints, typical…

Reinforcement Learning

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning

2023-03-07 · Nick Bührer, Zhejun Zhang, Alexander Liniger, Fisher Yu 외

An emerging field of sequential decision problems is safe Reinforcement Learning (RL), where the objective is to maximize the reward while obeying safety constraints. Being able to handle constraints is essential for dep…

Navigatereinforcement-learningReinforcement LearningReinforcement Learning (RL)+2