sweetice

dm_control

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

LibMTL

A PyTorch Library for Multi-Task Learning

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

awesome-offline-rl

An index of algorithms for offline reinforcement learning (offline-rl)

iris

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

curl

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

drq

DrQ: Data regularized Q

drqv2

DrQ-v2: Improved Data-Augmented Reinforcement Learning

realworldrl_suite

Real-World RL Benchmark Suite

TD3_BC

Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

phasic-policy-gradient

Code for the paper "Phasic Policy Gradient"

wrench

[NeurIPS 2021] WRENCH: Weak supeRvision bENCHmark

Evolutionary-Reinforcement-Learning

Codebase for Evolutionary Reinforcement Learning (ERL) from the paper "Evolution-Guided Policy Gradients in Reinforcement Learning" published at NeurIPS 2018

REDQ

Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.

sunrise

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

dice_rl

mpo

PyTorch Implementation of the Maximum a Posteriori Policy Optimisation

DA-in-visualRL

Collection of papers and resources for data augmentation (DA) in visual reinforcement learning (RL).

generalized_dt

Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)

curl_rainbow

revisiting-ppo

deep-successor-features-for-transfer

A reusable framework for successor features for transfer in deep reinforcement learning using keras.

OffCon3

📴 OffCon^3: SOTA PyTorch SAC and TD3 Implementations (arxiv: 2101.11331)

neural-approx-ss-lfi

Codes for ICLR 21 paper: Neural Approximate Sufficient Statistics for Implicit Models

KWNG

A Pytorch implementation of the KWNG estimator

LeagueSandbox-RL-Learning

Modified version of the LeagueSandbox project which relies on a Redis server to accept actions and send observations. Intended for reinforcement learning within v4.20 League of Legends.

WNPG

implementation of Wasserstein Natural Policy Gradients and Wasserstein Natural Evolution Strategies

ppg

Phasic Policy Gradient

adaptive_estimators

Code for ICLR 2019 paper "Adaptive Estimators Show Information Compression in Deep Neural Networks" (https://openreview.net/forum?id=SkeZisA5t7)