/DQN-pytorch

Collection of various DQN implementations from papers

Primary LanguagePythonMIT LicenseMIT

DQN-pytorch

Collection of DQN variations from papers, implemented in pytorch




--- Gif of gameplay here

DQN

Implementation of Human-level control through deep reinforcement learning

Summary

Using a convolutional neural network to take inputs, as well introducing a network termed experience replay, and only periodically updating the Q-value will allow the DQN to perform better than a standard naive DQN

Results

Pong results of DQN trained on 500 episodes

DDQN

Implementation of Deep Reinforcement Learning with Double Q-learning

Summary

Fix DQN's over-estimation of some action values by decoupling the selection from the evaluation of an action

Results

--- results comparison here