16 Repos
Awesome GitHub RepositoriesOffline RL Implementations
Open source software and libraries for offline reinforcement learning research.
Explore 16 awesome GitHub repositories matching part of an awesome list · Offline RL Implementations. Refine with filters or upvote what's useful.
Awesome Offline RL Implementations GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- vitchyr/rlkit
vitchyr/rlkit
2,910Auf GitHub ansehenReinforcement learning framework and algorithms implemented in PyTorch.
Accelerating online reinforcement learning with offline datasets.
Python - aviralkumar2907/cql
aviralkumar2907/CQL
Code for Conservative Q-Learning for Offline Reinforcement Learning (https://arxiv.org/abs/2006.04779)
Conservative Q-learning for offline reinforcement learning.
Python - tianheyu927/mopo
tianheyu927/mopo
Code to reproduce the experiments in MOPO: Model-based Offline Policy Optimization.
Model-based offline policy optimization for reinforcement learning.
Python - facebookresearch/vip
facebookresearch/vip
Jason Yecheng Ma 12 , Shagun Sodhani 1 Dinesh Jayaraman 2 , Osbert Bastani 2 , {Vikash Kumar 1 , Amy Zhang 1 }
Universal visual reward and representation learning via value-implicit pre-training.
Python - aviralkumar2907/bear
aviralkumar2907/BEAR
Update (07/17): We have released a cleaner implementation of BEAR on top of rlkit at: https://github.com/rail-berkeley/d4rl_evaluations, which goes with the latest version of the D4RL paper. We would encourage all users to use this new implementation as compared to this repo. We made…
Stabilizing off-policy Q-learning via bootstrapping error reduction.
Python - siemens/industrialbenchmark
siemens/industrialbenchmark
Industrial Benchmark
Robust offline deep reinforcement learning for industrial benchmarks.
Java - spitis/mrl
spitis/mrl
This is a modular RL code base for research. The intent is to enable surgical modifications by designing the base agent as a list of modules that all live inside the agent's global namespace (so they can all access each other directly by name). This means we can change the algorithm of a complex…
Counterfactual data augmentation using locally factored dynamics.
Python - wenxuan-zhou/plas
Wenxuan-Zhou/PLAS
This is the repository for our paper "PLAS: Latent Action Space for Offline Reinforcement Learning" in CoRL 2020. Please visit our website for more information.
Latent action space for offline reinforcement learning.
Python - avisingh599/cog
avisingh599/cog
This repository accompanies the following paper:
Connecting new skills to past experience with offline reinforcement learning.
Python - yudasong/hyq
yudasong/HyQ
This repository contains code for paper: Hybrid RL: Using both offline and online data can make RL efficient.
Hybrid reinforcement learning framework using both offline and online data.
Python - albertwilcox/mcac
albertwilcox/mcac
Author implementation of 'Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations'
Monte Carlo augmented actor-critic for sparse reward deep reinforcement learning.
Python - tung-nd/cwbc
tung-nd/cwbc
Dependencies can be installed with the following command:
Conservative behavioral cloning for reliable offline reinforcement learning.
Python - limengbinggz/cusum-rl
limengbinggz/CUSUM-RL
This repository contains the implementation for the AoS paper "Testing Stationarity and Change Point Detection in Reinforcement Learning" in Python (and R for plotting).
Reinforcement learning framework for nonstationary environments.
Python - danieltakeshi/dcur
DanielTakeshi/DCUR
This is the code used for the paper:
Data curriculum for teaching via samples with reinforcement learning.
Python - eladsar/rbi
eladsar/rbi
Implementation of distributed RL algorithms:
Batch residual policy optimization for reinforcement learning.
Python - jayanthrr/rc-offlinerl
JayanthRR/RC-OfflineRL
Offline reinforcement learning with resource-constrained online deployment.
