Skip to content

Instantly share code, notes, and snippets.

View Shmuma's full-sized avatar

Max Lapan Shmuma

View GitHub Profile
Slow version: https://github.com/Shmuma/rl/blob/master/test-1/a3c_atari.py
https://github.com/Shmuma/rl/blob/master/algos/a3c_async.py
Genetical algorythm with mutations probability decay.
https://github.com/Shmuma/Practical_RL/blob/master/week0/frozen-8x8.ipynb
Crossentropy method
https://github.com/Shmuma/Practical_RL/blob/master/week1/taxi_crossentropy.ipynb
Crossentropy method with dense NN 40+40
https://github.com/Shmuma/Practical_RL/blob/master/week1/MountainCar-xentropy.ipynb
Uses ptan library: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay.py
Config for the run: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_cartpole.ini
DQN with experience replay.
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_corridor.ini
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_basic.ini
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_health.ini
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_defend_center.ini