PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

PyTorch C++ Reinforcement Learning

PyTorch implementation of Trust Region Policy Optimization

PyTorch Implementation of REINFORCE for both discrete & continuous control

Code for the paper "Evolved Policy Gradients"

Tensorflow implementation of generative adversarial imitation learning

PyTorch implementation of Soft Actor-Critic (SAC)

Implement A3C for Mujoco gym envs

End to end motion planner using Deep Deterministic Policy Gradient (DDPG) in gazebo

A workbench for online model-free Reinforcement Learning on continuous control problems

Catalyst.RL: A Distributed Framework for Reproducible RL Research

Deep Reinforcement Learning with pytorch & visdom (the branch for A3C continuous control)

PyTorch Implementation of the RDPG (Recurrent Deterministic Policy Gradient)

Learning Continuous Control in Deep Reinforcement Learning

Simple and self-contained TensorFlow implementation of reinforcement learning algorithms for continuous control, integrated with OpenAI Gym and other physics engines.

PyTorch implementation of some reinforcement learning algorithms: Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), V-MPO, Behavior Cloning (BC). More algorithms will be added.

Whitelist intentionally-public buckets, block everything else

RLbox: Solving OpenAI Gym with TensorFlow

Reinforcement learning with musculoskeletal models

Neural Ordinary Differential Equations for Reinforcement Learning

Implementation of Deep Bayesian Quadrature Policy Optimization (https://arxiv.org/abs/2006.15637) :- A modular source code for on-policy policy gradient algorithms.

This repository provides a simulation of 4-Room-World environment.

A Jitterbug dm_control Reinforcement Learning domain

TensorFlow Implementation of Deep Deterministic Policy Gradients for Continuous OpenAI Gym Environments

Continuous Control using DDPG Algorithm

Examples of lambda solutions

Implementation of the DDPG algorithm to solve Continuous Control Reacher Environment

Implementation of Deep RL algorithms for continuous-control tasks

experiences with parity

Train agents to walk, drive.. by themself using Unity ML Agent, OpenAI Gym and PyTorch