jemaw / gym-safety
Simple gym environments for safety in Reinforcement Learning Research
☆15Updated 6 months ago
Alternatives and similar repositories for gym-safety:
Users that are interested in gym-safety are comparing it to the libraries listed below
- Code for a model-based version of Constrained Policy Optimization☆10Updated 3 years ago
- Pytorch Implementation for First Order Constrained Optimization in Policy Space (FOCOPS).☆27Updated 3 years ago
- An implementation of Constrained Policy Optimization (Achiam 2017) in PyTorch☆23Updated 4 years ago
- Simple maze environments using mujoco-py☆54Updated last year
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆102Updated 2 years ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆64Updated last year
- Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'☆57Updated 3 years ago
- ☆14Updated 3 years ago
- We investigate the effect of populations on finding good solutions to the robust MDP☆28Updated 3 years ago
- ☆119Updated 5 months ago
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆159Updated 2 years ago
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆42Updated 4 months ago
- NeurIPS Reproducibility Challenge 2019☆20Updated 4 years ago
- Author's PyTorch implementation of TD7 for online and offline RL☆122Updated last year
- Benchmarking RL generalization in an interpretable way.☆138Updated 11 months ago
- ☆28Updated 2 years ago
- ☆54Updated 10 months ago
- Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL, published in ICLR 2023☆29Updated last month
- Code for MOPO: Model-based Offline Policy Optimization☆173Updated 2 years ago
- ☆42Updated 3 years ago
- Submission for MAVEN: Multi-Agent Variational Exploration☆56Updated 2 years ago
- Mirror Descent Policy Optimization☆37Updated 4 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆64Updated last year
- Offline Risk-Averse Actor-Critic (O-RAAC). A model-free RL algorithm for risk-averse RL in a fully offline setting☆33Updated 3 years ago
- The official code base of Shared Experience Actor-Critic (NeurIPS2020)☆35Updated 10 months ago
- Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)☆73Updated 2 years ago
- ☆47Updated 3 years ago
- ☆30Updated 5 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆85Updated 3 years ago
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆36Updated last week