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).

reinforcement-learning deep-learning deep-reinforcement-learning pytorch atari hessian second-order continuous-control actor-critic ale mujoco proximal-policy-optimization ppo advantage-actor-critic a2c acktr natural-gradients roboschool kfac kronecker-factored-approximation

• Updated May 29, 2022
• Python

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

board-game reinforcement-learning pytorch gym mcts gomoku tictactoe atari alpha-beta-pruning monte-carlo-tree-search continuous-control board-games alphazero self-play mcts-algorithm muzero stochastic-muzero efficientzero sampled-muzero gumbel-muzero

• Updated Oct 15, 2026
• Python

The Fastest Deep Reinforcement Learning Library

reinforcement-learning deep-learning cpp robotics continuous-control mujoco tinyml tinyrl

• Updated Nov 9, 2026
• C++

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

reinforcement-learning deep-learning deep-reinforcement-learning gym flax behavioral-cloning sac continuous-control deep-deterministic-policy-gradient jax soft-actor-critic offline-reinforcement-learning batch-reinforcement-learning

• Updated Oct 26, 2022
• Jupyter Notebook

PyTorch implementation of Soft Actor-Critic (SAC)

reinforcement-learning deep-learning deep-reinforcement-learning pytorch gym sac continuous-control actor-critic mujoco dm-control soft-actor-critic d4pg

• Updated Dec 5, 2021
• Jupyter Notebook

PyTorch C++ Reinforcement Learning

reinforcement-learning cplusplus cpp pytorch reinforcement-learning-algorithms continuous-control actor-critic pytorch-rl proximal-policy-optimization ppo advantage-actor-critic a2c libtorch pytorch-cpp-frontend

• Updated May 3, 2020
• C++

PyTorch implementation of Trust Region Policy Optimization

reinforcement-learning deep-learning deep-reinforcement-learning pytorch continuous-control trpo mujoco trust-region-policy-optimization

• Updated Sep 13, 2018
• Python

PyTorch Implementation of REINFORCE for both discrete & continuous control

reinforcement-learning pytorch gym reinforce continuous-control mujoco

• Updated Apr 16, 2017
• Python

Code for the paper "Evolved Policy Gradients"

machine-learning reinforcement-learning paper evolutionary-strategy continuous-control meta-learning

• Updated Nov 22, 2018
• Python

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

deep-learning neural-network navigation tensorflow deep-reinforcement-learning gazebo ddpg continuous-control ros-kinetic motion-planner deep-deterministic-policy-gradient turtlebot3

• Updated Nov 23, 2022
• Python

Tensorflow implementation of generative adversarial imitation learning

reinforcement-learning tensorflow generative-adversarial-network imitation-learning inverse-reinforcement-learning continuous-control trpo gail

• Updated Apr 23, 2018
• Python

Official PyTorch code for "Recurrent Off-policy Baselines for Memory-based Continuous Control" (DeepRL Workshop, NeurIPS 21)

reinforcement-learning pytorch continuous-control actor-critic rdpg recurrent-neural-network off-policy rtd3 rsac

• Updated Nov 21, 2023
• Python

Implement A3C for Mujoco gym envs

reinforcement-learning pytorch a3c continuous-control actor-critic mujoco

• Updated Nov 2, 2017
• Python

PyTorch Implementation of the RDPG (Recurrent Deterministic Policy Gradient)

deep-reinforcement-learning pytorch recurrent-neural-networks continuous-control rdpg

• Updated Dec 8, 2022
• Python

Catalyst.RL: A Distributed Framework for Reproducible RL Research

python benchmark framework reinforcement-learning deep-learning pytorch continuous-control mujoco

• Updated Mar 17, 2019
• Python

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

windows linux distributed-systems reinforcement-learning cntk continuous-control

• Updated Jul 5, 2023
• C++

Official PyTorch implementation of "DC-MPC: Discrete Codebook Model Predictive Control"

reinforcement-learning representation-learning continuous-control model-predictive-control model-based-reinforcement-learning world-models deepmind-control-suite meta-world model-predictive-path-integral myosuite

• Updated Mar 15, 2025
• Jupyter Notebook

Benchmark data (i.e., DeepMind Control Suite and MuJoCo) for RL.

reinforcement-learning ddpg sac continuous-control dmc mujoco ppo benchmark-data td3

• Updated Jan 23, 2021
• Python

PyTorch implementation of the Q-Learning Algorithm Normalized Advantage Function for continuous control problems + PER and N-step Method

reinforcement-learning q-learning dqn reinforcement-learning-algorithms continuous-control naf ddpg-algorithm prioritized-experience-replay normalized-advantage-functions q-learning-algorithm n-step-bootstrapping

• Updated Feb 16, 2021
• Jupyter Notebook

Proximal Policy Optimization (Continuous Version) in PyTorch.

continuous-control ppo

• Updated May 12, 2025
• Python