Reinforcement Learning Applied by Pytorch.
Temporal Difference Based RL Methods
- For push box game, you should config your gym environment, then run the following commands.
cd temporal_difference
cd push_box_game
python main.py
- For the maze game, just run the following commands.
cd temporal_difference
cd morvan_maze_game
python QLearning.py
python Sarsa.py
Value Function Approximate
cd value_functoin_approximate
cd DQN
python DQN_Maze_Env.py