car-racing-drl

using method of deep deterministic policy gradient (DDPG) to solve the CarRacing-v0 in gym
The method is based upon the paper: CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
.gitignore		.gitignore
README.md		README.md
before_training.py		before_training.py
ddpg_car-racing.py		ddpg_car-racing.py
ddpg_discrete.py		ddpg_discrete.py
dqn_discrete.py		dqn_discrete.py
dqn_rnn_discrete.py		dqn_rnn_discrete.py
dqn_rnn_test.py		dqn_rnn_test.py
dqn_test.py		dqn_test.py
pg_discrete.py		pg_discrete.py
pg_pong.py		pg_pong.py
replay_buffer_ddpg.py		replay_buffer_ddpg.py
replay_buffer_dqn.py		replay_buffer_dqn.py

Provide feedback