Build software better, together

denisyarats / drq

DrQ: Data regularized Q

python control reinforcement-learning deep-learning pixel deep-reinforcement-learning pytorch gym rl data-augmentation sac actor-critic mujoco model-free off-policy dm-control drq soft-actor-crit

Updated Jan 13, 2023
Jupyter Notebook

MishaLaskin / rad

Star

RAD: Reinforcement Learning with Augmented Data

Updated Mar 29, 2021
Jupyter Notebook

UniBwTAS / ccma

Star

Curvature Corrected Moving Average: An accurate and model-free path smoothing algorithm.

Updated Dec 23, 2025
Python

denisyarats / exorl

Star

ExORL: Exploratory Data for Offline Reinforcement Learning

python control reinforcement-learning deep-learning pytorch datasets mujoco model-free off-policy offline-rl unsupevised exporation

Updated Feb 8, 2022
Python

pokaxpoka / sunrise

Star

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

deep-neural-networks reinforcement-learning deep-learning deep-reinforcement-learning rainbow rl codebase deep-q-network sac deep-q-learning mujoco model-free off-policy dm-control soft-actor-critic

Updated Mar 21, 2021
Python

lucidrains / SAC-pytorch

Star

Implementation of Soft Actor Critic and some of its improvements in Pytorch

reinforcement-learning deep-learning robotics artificial-intelligence model-free

Updated Sep 24, 2026
Python

Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"

agent wrapper natural-language-processing reinforcement-learning robotics simulation cup rainbow pytorch a3c transfer-learning cups multi-task-learning model-based model-free simulated-environments natural-language-instructions ai2thor-environment openai-gym-interface

Updated Mar 9, 2020
Python

ewanlee / ICLR2019-RL-Papers

Star

The Reinforcement-Learning-Related Papers of ICLR 2019

reinforcement-learning transfer-learning imitation-learning online-learning hierarchical-reinforcement-learning inverse-reinforcement-learning multiagent-reinforcement-learning meta-learning model-based-rl model-free iclr2019 intrinsic-reward robust-reinforcement-learning sequence-modeling

Updated May 28, 2019

IRVLUTD / SceneReplica

Star

Code release for SceneReplica paper.

benchmark robotics manipulation model-based model-free

Updated Jul 24, 2025
Python

fedebotu / vision-cartpole-dqn

Star

Implementation of the CartPole from OpenAI's Gym using only visual input for Reinforcement Learning control with DQN

reinforcement-learning computer-vision openai-gym dqn cartpole inverted-pendulum model-free model-free-rl model-free-control vision-cartpole

Updated Apr 8, 2021
Jupyter Notebook

hassaanhashmi / pd_zdpg_plus

Star

Code for IEEE MLSP 2021 paper titled "Model-Free Learning of Optimal Deterministic Resource Allocations in Wireless Systems via Action-Space Exploration"

reinforcement-learning policy-gradient wireless resource-allocation model-free zeroth-order-optimization

Updated Nov 9, 2022
Python

albert100121 / MLVR-Pytorch

Star

A Pytorch implementation of The Visual Centrifuge: Model-Free Layered Video Representations.

deep-neural-networks video deep-learning pytorch frame cvpr 3d-convolutional-network 3d-cnn model-free i3d pytorch-implementation cvpr2019 cvpr19 3d-convolutions 3d-conv i3d-inception-architecture mlvr inception3d

Updated Aug 14, 2020
Python

bmaxdk / DeepRL-ND-Continuous-Control

Star

DDPG and D4PG Continuous Control

unity deep-reinforcement-learning openai-gym pytorch ddpg-algorithm model-free off-policy d4pg-algorithm

Updated Jul 13, 2023
ASP.NET

rssalessio / ModelFreeActiveExplorationRL

Star

This repository hosts the code accompanying the paper "Model-Free Active Exploration in Reinforcement Learning". Our study approaches the exploration problem in Reinforcement Learning (RL) from an information-theoretical viewpoint and presents a novel, efficient, and entirely model-free solution.

python reinforcement-learning exploration model-free best-policy-identification mfbpi dbmfbpi

Updated Nov 18, 2023
Jupyter Notebook

fedebotu / a3c-flappy-bird

Star

Deep Reinforcement Learning implementation in Keras of an AI controlling the popular Flappy Bird videogame, using Asynchronous Advantage Actor Critic (A3C)

reinforcement-learning flappy-bird deep-reinforcement-learning a3c model-free model-free-rl

Updated Dec 22, 2020
Python

LauraSparacino / SIR_toolbox

Star

The SIR Matlab Toolbox performs computation of time and frequency domain information measures of entropy rate (ER), mutual information rate (MIR) and O-Information rate (OIR), exploiting both parametric and non-parametric estimation of the power spectral density of (blocks of) interacting stochastic processes.