Keras Implementation of PPO to solve OpenAI Gym Environments

My implementation of the Proximal Policy Optisation algorithm using Keras as a backend

Reinforcement learning algorithms implemented for Tensorflow 2.0+ [DQN, DDPG, AE-DDPG, SAC, PPO, Primal-Dual DDPG]

Code for Efficient Continuous Control with Double Actors and Regularized Critics, AAAI 2022.