microsoft / ATACLinks
Code accompanying the paper Adversarially Trained Actor Critic for Offline Reinforcement Learning by Ching-An Cheng*, Tengyang Xie*, Nan Jiang, and Alekh Agarwal.
☆72Updated 2 years ago
Alternatives and similar repositories for ATAC
Users that are interested in ATAC are comparing it to the libraries listed below
Sorting:
- Code for MOPO: Model-based Offline Policy Optimization☆190Updated 3 years ago
- ☆54Updated last year
- Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning☆29Updated 3 years ago
- ☆58Updated 2 years ago
- [ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"☆35Updated 2 years ago
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆181Updated 3 years ago
- Benchmarked implementations of Offline RL Algorithms.☆76Updated 9 months ago
- Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)☆80Updated 3 years ago
- [NeurIPS 2022 Oral] The official implementation of POR in "A Policy-Guided Imitation Approach for Offline Reinforcement Learning"☆57Updated 2 years ago
- Model-Based Offline Reinforcement Learning☆51Updated 4 years ago
- Conservative Q Learning on top of SAC☆132Updated 3 years ago
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆152Updated 4 years ago
- Code for FOCAL Paper Published at ICLR 2021☆52Updated 2 years ago
- Code for Latent Action Space for Offline Reinforcement Learning [CoRL 2020]☆53Updated 4 years ago
- Official code for "RAMBO: Robust Adversarial Model-Based Offline RL", NeurIPS 2022☆31Updated 2 years ago
- ☆44Updated 4 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated 2 years ago
- Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.☆176Updated last year
- Author's PyTorch implementation of TD7 for online and offline RL☆154Updated 2 years ago
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆38Updated 2 years ago
- Offline Risk-Averse Actor-Critic (O-RAAC). A model-free RL algorithm for risk-averse RL in a fully offline setting☆35Updated 4 years ago
- ExORL: Exploratory Data for Offline Reinforcement Learning☆118Updated 3 years ago
- Code for MOBILE: Model-Bellman Inconsistency Penalized Offline Policy Optimization☆22Updated last year
- Inverse Reinforcement Learning via State Marginal Matching, CoRL 2020☆45Updated 2 years ago
- ☆18Updated 3 years ago
- Random parameter environments using gym 0.7.4 and mujoco-py 0.5.7☆20Updated 6 years ago
- Simple maze environments using mujoco-py☆57Updated last year
- Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.☆132Updated 4 years ago
- Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination☆26Updated 3 years ago
- Conservative Q learning in Jax☆56Updated 2 years ago