aviralkumar2907 / BEARLinks
Code for Stabilizing Off-Policy RL via Bootstrapping Error Reduction
☆161Updated 5 years ago
Alternatives and similar repositories for BEAR
Users that are interested in BEAR are comparing it to the libraries listed below
Sorting:
- ☆199Updated 2 years ago
- ☆92Updated last year
- Code for MOPO: Model-based Offline Policy Optimization☆182Updated 3 years ago
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning☆125Updated 4 years ago
- Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.☆171Updated 8 months ago
- ☆61Updated 7 years ago
- Unofficial Pytorch code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"☆190Updated 2 years ago
- Learning to Adapt in Dynamic, Real-World Environment through Meta-Reinforcement Learning☆214Updated 2 years ago
- ☆132Updated last year
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆69Updated last year
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆149Updated 3 years ago
- ☆274Updated 7 years ago
- Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)☆192Updated 2 years ago
- Implementation of Proximal Meta-Policy Search (ProMP) as well as related Meta-RL algorithm. Includes a useful experiment framework for Me…☆238Updated 2 years ago
- This repository contains the code to implement the Hierarchical Actor-Critic (HAC) algorithm.☆259Updated 5 years ago
- DHER: Hindsight Experience Replay for Dynamic Goals (ICLR-2019)☆66Updated 5 years ago
- ☆113Updated 2 years ago
- ☆99Updated 2 years ago
- ☆111Updated 5 years ago
- Explorer is a PyTorch reinforcement learning framework for exploring new ideas.☆95Updated last month
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆174Updated 3 years ago
- Model-Based Offline Reinforcement Learning