acyclics / MPO
Pytorch implementation of "Maximum a Posteriori Policy Optimization" with Retrace for Discrete gym environments
☆27Updated 4 years ago
Alternatives and similar repositories for MPO:
Users that are interested in MPO are comparing it to the libraries listed below
- PyTorch Implementation of the Maximum a Posteriori Policy Optimisation☆74Updated 2 years ago
- Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238☆45Updated 4 years ago
- Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)☆67Updated 2 years ago
- ☆42Updated 2 years ago
- ☆31Updated 4 years ago
- ☆17Updated 3 years ago
- on-policy optimization baselines for deep reinforcement learning☆30Updated 5 years ago
- ☆22Updated 2 years ago
- V-MPO torch version with DMLab30 and GTrXL☆13Updated 4 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- DecentralizedLearning☆24Updated 2 years ago
- Codebase for BRDiv: Diverse teammate generation for ad hoc teamwork☆13Updated 11 months ago
- ☆26Updated 2 years ago
- Implementation of ICML2020 paper <Bidirectional Model-based Policy Optimization>☆23Updated 2 years ago
- ☆53Updated last year
- ☆55Updated 2 years ago
- Code for NeurIPS 2021 paper "Curriculum Offline Imitation Learning"☆18Updated 2 years ago
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆62Updated last year
- Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]☆47Updated 2 years ago
- MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.☆46Updated last year
- The official repository of Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration" (AAMAS 2022)☆27Updated 3 years ago
- Advantage weighted Actor Critic for Offline RL☆50Updated 2 years ago
- Code for "Hierarchical Skills for Efficient Exploration" HSD-3 Algorithm and Baselines☆49Updated 2 years ago
- We investigate the effect of populations on finding good solutions to the robust MDP☆28Updated 4 years ago
- ☆18Updated 2 years ago
- Github repo for HIDIO: Hierarchical Reinforcement Learning by Discovering Intrinsic Options☆45Updated 3 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
- Authors' PyTorch implementation of 'Recomposing the Reinforcement Learning Building-Blocks with Hypernetworks' (HypeRL)☆25Updated 3 years ago
- ☆15Updated 2 years ago
- IV-RL - Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation☆40Updated 5 months ago