Chapter notes and exercise solutions for Reinforcement Learning: An Introduction by Sutton and Barto

A novel method to incorporate existing policy (Rule-based control) with Reinforcement Learning.

A reinforcement learning A3C implementation trained to play Super Mario Bros

Control Methods for Dynamic Systems based on Neural Networks

Code for paper "Computation Offloading Optimization for UAV-assisted Mobile Edge Computing: A Deep Deterministic Policy Gradient Approach"

Reinforcement Learning - PPO (Proximal Policy Optimization) Implementation to Pong Game

强化学习算法库，包含了目前主流的强化学习算法(Value based and Policy based)的代码，代码都经过调试并可以运行

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

This simulator implements the "Fictitious Mean-field Reinforcement-Learning" for Q-learning, Actor Critic and Stochastic Gradient Ascent algorithms in a distributed system. The setting includes strategic agents who compete over a set of heterogenous servers. Through experiments, we show that it outperforms the naive deployment of each RL algorithm.

A Universal Deep Reinforcement Learning Framework

This Repository contains my projects!

Solutions of assignments of Deep Reinforcement Learning course presented by the University of California, Berkeley (CS285) in Pytorch framework

Programming Assignments for Reinforcement Learning Specialization

A very detailed project of Chrome Dinosaur in Deep RL for beginners

A trading bitcoin agent was created with deep reinforcement learning implementations.

Master MVA - Reinforcement Learning Project

A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

PyTorch implementation of D4PG with the SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

A Deep Deterministic Policy Gradient Actor-Critic reinforcement learning solution to the Unity-ML(Udacity) Reacher environment