gwthomas / Safe-MBPO
Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"
☆43Updated 2 years ago
Alternatives and similar repositories for Safe-MBPO:
Users that are interested in Safe-MBPO are comparing it to the libraries listed below
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆64Updated last year
- ☆70Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆64Updated last year
- Code accompanying the paper "Action Robust Reinforcement Learning and Applications in Continuous Control" https://arxiv.org/abs/1901.0918…☆42Updated 5 years ago
- Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.☆34Updated 2 years ago
- Implementations of SAILR, PDO, and CSC☆31Updated 7 months ago
- Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning☆23Updated last year
- Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.☆55Updated last year
- Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.☆54Updated 8 months ago
- ☆54Updated 2 years ago
- Code for Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations☆18Updated 2 years ago
- The official repository of Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration" (AAMAS 2022)☆27Updated 3 years ago
- Implementations of safe reinforcement learning algorithms☆26Updated 11 months ago
- Code release for the paper "Towards Safe Reinforcement Learning with a Safety Editor Policy", Yu et al., arXiv 2022☆13Updated last year
- We investigate the effect of populations on finding good solutions to the robust MDP☆28Updated 3 years ago
- Curricular Subgoal for Inverse Reinforcement Learning☆13Updated last year
- Model-Free Safe Reinforcement Learning through Neural Barrier Certificate☆32Updated 9 months ago
- Offline Risk-Averse Actor-Critic (O-RAAC). A model-free RL algorithm for risk-averse RL in a fully offline setting☆34Updated 4 years ago
- Code for "On the Robustness of Safe Reinforcement Learning under Observational Perturbations" (ICLR 2023)☆44Updated 2 months ago
- Official implementation of the paper: Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate☆20Updated last year
- [ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"☆34Updated 2 years ago
- behavior cloning from observation☆35Updated 4 years ago
- DecentralizedLearning☆23Updated 2 years ago
- Inverse Reinforcement Learning via State Marginal Matching, CoRL 2020☆44Updated last year
- Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.☆19Updated 2 years ago
- Code for the paper "WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning"☆51Updated last year
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆85Updated 5 months ago
- Code for "Constrained Variational Policy Optimization for Safe Reinforcement Learning" (ICML 2022)☆69Updated last year
- ☆14Updated 2 years ago
- [ICLR 2022 Spotlight] Code for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration☆26Updated 3 years ago