PyTorch Implementation of REINFORCE for both discrete & continuous control

My thesis work on exploring the performance impact of the exploration strategy

My reports for the reinforcement learning class given at the ENS

Implementations of solutions to the continuous mountain car problem. Using OpenAI Gym and Tensorflow 1.1.

Stochastic Policy Gradient algorithm branched from keon's project, fixed softmax, one-hot coding, and CE loss issues.

Chainer implementation of Deepmind's Visual Attention Model paper

Reinforcement Learning projects from OpenAI Gym

simple and compact implementations of reinforcement learning benchmark algorithms

Simple, well-commented Pytorch implementations of REINFORCE and Actor Critic RL methods.

自动加固Android App

Bandit learning on top of Neural Monkey, an open-source tool for sequence learning in NLP built on TensorFlow. Bandit online learning objectives in branch bandits-acl (ACL17) and counterfactual learning objectives in branch acl-2018 (ACL18).

PyTorch Implementations of Standard Deep RL Algorithms (including REINFORCE, A2C, PPO)

Implementation of Reinforcement Algorithms from scratch

Reinforcement Learning agents for the game of Hex

Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359

OpenAI Gym's Cartpole environment REINFORCE algorithm implementation