-
Datasets and Benchmarks for Offline Safe Reinforcement Learning
A comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning... -
Verification-Guided Shielding for Deep Reinforcement Learning
The dataset used in the paper is a set of benchmarks for safe deep reinforcement learning. The benchmarks include Particle World and Mapless Navigation. -
OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Rese...
OmniSafe is a comprehensive infrastructural framework designed to accelerate Safe Reinforcement Learning research. -
Bullet-Safety-Gym
The Bullet-Safety-Gym provides a set of tasks for safe reinforcement learning.
