Skip to content

Instantly share code, notes, and snippets.

@ceteri

ceteri/rl22.py

Last active July 7, 2020 06:38
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ceteri/07979d0fc68f7f79fed2b71347e598ea to your computer and use it in GitHub Desktop.
Save ceteri/07979d0fc68f7f79fed2b71347e598ea to your computer and use it in GitHub Desktop.
Download ZIP
Raw
rl22.py
SELECT_ENV = "MountainCar-v0"
config = ppo.DEFAULT_CONFIG.copy()
config["log_level"] = "WARN"
config["num_workers"] = 4 # default = 2
config["train_batch_size"] = 10000 # default = 4000
config["sgd_minibatch_size"] = 256 # default = 128
config["evaluation_num_episodes"] = 50 # default = 10
agent = ppo.PPOTrainer(config, env=SELECT_ENV)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment