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:
- Linear Q network without experience replay
- Linear Q network with experience replay
- Deep D-network (DQN) with experience replay and target network
- Dueling DQN with experience replay
- Double Dueling DQN with conv layers, specially tweaked for playing Space_Invaders_v0