Skip to content

A repository of Q-learning based Deep Reinforcement learning algorithms, including Linear DQN, DQN with experience reply, Dueling DQN and Double Dueling DQN. Mostly tested on Gym environments.

Notifications You must be signed in to change notification settings

shubhamag/DeepRL_DQN_tensorflow

Repository files navigation

DeepRL_DQN_tensorflow

A repository of Q-learning based Deep Reinforcement learning algorithms, including Linear DQN, DQN with experience reply, Dueling DQN and Double Dueling DQN. Tested on Tensorflow + Gym.

Implemented algorithms:

  1. Linear Q network without experience replay
  2. Linear Q network with experience replay
  3. Deep D-network (DQN) with experience replay and target network
  4. Dueling DQN with experience replay
  5. Double Dueling DQN with conv layers, specially tweaked for playing Space_Invaders_v0

About

A repository of Q-learning based Deep Reinforcement learning algorithms, including Linear DQN, DQN with experience reply, Dueling DQN and Double Dueling DQN. Mostly tested on Gym environments.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages