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 implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.

ROS 2 enabled Machine Learning algorithms

☔ Deep RL agents with PyTorch☔

Minimal Implementation of Deep RL Algorithms in PyTorch

Distributed Online Service Coordination Using Deep Reinforcement Learning

Deep reinforcement learning framework for fast prototyping based on PyTorch

Interfacing RL agents with user-definable neural networks and OpenAI-gym environments.

Exhaustive Implementation of Algorithms, Key Papers, and Well-Known Problems of Reinforcement Leaning

Some model free RL algorithms

Implementation of A2C and ACKTR in TensorFlow.

Teaching a neural network how to write letters and digits with reinforcement learning.

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR). Python2 compatible (branch python2)

ROS 2 enabled Machine Learning algorithms

Handmade environments and trained models.

Playing Super Mario Bros with Advantage Actor Critic (A2C), Asynchronous Advantage Actor Critic (A3C) and Actor Critic using Kronecker-Factored Trust Region (ACKTR)