Unreal environments for reinforcement learning

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

Official PyTorch implementation of "Entity-Centric Reinforcement Learning for Object Manipulation from Pixels", Haramati et al., ICLR 2024

Official pytorch implementation of the paper [Environment Agnostic Representation for Visual Reinforcement learning]

Official release of the DMControl Generalization Benchmark 2 (DMC-GB2)

[ICLR 2024] Adaptive Replay Ratio implementation from 'Revisiting Plasticity in Visual RL: Data, Modules and Training Stages'.

Implementation of the DQN and DRQN algorithms in Keras and tensorflow

Original PyTorch implementation of experiments in paper 'Normalization Enhances Generalization in Visual Reinforcement Learning'.

The official implementation of the ECCV 2024 paper "Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL"

[NeurIPS 2023] CycAug implementation from paper 'Learning Better with Less: Effective Augmentation for Sample-Efficient Visual RL'.

This repository offers implementations of classic and deep reinforcement learning algorithms, including dynamic programming, monte carlo methods, td-learning, and also both q-function-based and policy gradient approaches with deep nerual networks.

This is a fork of "RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization" to make it more portable for ease of use in research. The goal of this repository is to provide an easier way to install RL-ViGen environments (only envs) in already established repos with minimal dependencies.

Small prototype to show RoboHive usage with TorchRL for visual deep reinforcement learning