SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

by   Linrui zhang, et al.

Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well. Considering the distinctiveness of this community, efficient and reproducible baselines are still lacking for safe AD. In this paper, we release SafeRL-Kit to benchmark safe RL methods for AD-oriented tasks. Concretely, SafeRL-Kit contains several latest algorithms specific to zero-constraint-violation tasks, including Safety Layer, Recovery RL, off-policy Lagrangian method, and Feasible Actor-Critic. In addition to existing approaches, we propose a novel first-order method named Exact Penalty Optimization (EPO) and sufficiently demonstrate its capability in safe AD. All algorithms in SafeRL-Kit are implemented (i) under the off-policy setting, which improves sample efficiency and can better leverage past logs; (ii) with a unified learning framework, providing off-the-shelf interfaces for researchers to incorporate their domain-specific knowledge into fundamental safe RL methods. Conclusively, we conduct a comparative evaluation of the above algorithms in SafeRL-Kit and shed light on their efficacy for safe autonomous driving. The source code is available at \href{}{this https URL}.


page 3

page 8


Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization

Reinforcement learning (RL) is attracting increasing interests in autono...

Safe Distributional Reinforcement Learning

Safety in reinforcement learning (RL) is a key property in both training...

Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach

Emerging applications in robotics and autonomous systems, such as autono...

Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving

Reinforcement learning (RL) has shown to reach super human-level perform...

Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Safety comes first in many real-world applications involving autonomous ...

How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies

Autonomous driving has the potential to revolutionize mobility and is he...

State-wise Safe Reinforcement Learning: A Survey

Despite the tremendous success of Reinforcement Learning (RL) algorithms...

Please sign up or login with your details

Forgot password? Click here to reset