Skip to content

Latest commit

 

History

History
 
 

examples

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 
blackjack_dqn.py
blackjack_dqn.py
 
 
blackjack_dqn_multi_process.py
blackjack_dqn_multi_process.py
 
 
blackjack_random.py
blackjack_random.py
 
 
blackjack_random_multi_process.py
blackjack_random_multi_process.py
 
 
doudizhu_dqn.py
doudizhu_dqn.py
 
 
doudizhu_nfsp.py
doudizhu_nfsp.py
 
 
doudizhu_random.py
doudizhu_random.py
 
 
gin_rummy_dqn.py
gin_rummy_dqn.py
 
 
gin_rummy_human.py
gin_rummy_human.py
 
 
gin_rummy_nfsp.py
gin_rummy_nfsp.py
 
 
gin_rummy_random.py
gin_rummy_random.py
 
 
gin_rummy_random_gui.py
gin_rummy_random_gui.py
 
 
leduc_holdem_br.py
leduc_holdem_br.py
 
 
leduc_holdem_cfr.py
leduc_holdem_cfr.py
 
 
leduc_holdem_dqn.py
leduc_holdem_dqn.py
 
 
leduc_holdem_dqn_pytorch.py
leduc_holdem_dqn_pytorch.py
 
 
leduc_holdem_exp.py
leduc_holdem_exp.py
 
 
leduc_holdem_human.py
leduc_holdem_human.py
 
 
leduc_holdem_nfsp.py
leduc_holdem_nfsp.py
 
 
leduc_holdem_nfsp_load_model.py
leduc_holdem_nfsp_load_model.py
 
 
leduc_holdem_nfsp_load_model_2.py
leduc_holdem_nfsp_load_model_2.py
 
 
leduc_holdem_nfsp_pytorch.py
leduc_holdem_nfsp_pytorch.py
 
 
leduc_holdem_nfsp_pytorch_load_model.py
leduc_holdem_nfsp_pytorch_load_model.py
 
 
leduc_holdem_nfsp_pytorch_load_model_2.py
leduc_holdem_nfsp_pytorch_load_model_2.py
 
 
leduc_holdem_random.py
leduc_holdem_random.py
 
 
leduc_holdem_random_multi_process.py
leduc_holdem_random_multi_process.py
 
 
leduc_holdem_single.py
leduc_holdem_single.py
 
 
limit_holdem_dqn.py
limit_holdem_dqn.py
 
 
limit_holdem_nfsp.py
limit_holdem_nfsp.py
 
 
limit_holdem_random.py
limit_holdem_random.py
 
 
mahjong_dqn.py
mahjong_dqn.py
 
 
mahjong_nfsp.py
mahjong_nfsp.py
 
 
mahjong_random.py
mahjong_random.py
 
 
nolimit_holdem_dqn.py
nolimit_holdem_dqn.py
 
 
nolimit_holdem_human.py
nolimit_holdem_human.py
 
 
nolimit_holdem_nfsp.py
nolimit_holdem_nfsp.py
 
 
nolimit_holdem_random.py
nolimit_holdem_random.py
 
 
simple_doudizhu_random.py
simple_doudizhu_random.py
 
 
uno_dqn.py
uno_dqn.py
 
 
uno_human.py
uno_human.py
 
 
uno_nfsp.py
uno_nfsp.py
 
 
uno_random.py
uno_random.py
 
 
uno_single.py
uno_single.py
 
 

README.md

Examples

We provide some running examples. We will update the examples if we achieve better results on large games such as Dou Dizhu, UNO and Mahjong.

  • blackjack_dqn.py: train DQN on Blackjack.
  • blackjack_dqn_multi_process.py: train DQN on Blackjack with multiple processes.
  • blackjack_random.py: run random agents on Blackjcak.
  • doudizhu_dqn.py: train DQN on Dou Dizhu.
  • doudizhu_nfsp.py: train NFSP on Dou Dizhu.
  • doudizhu_random.py: run random agents on Dou Dizhu.
  • doudizhu_random_multi_process.py: run random agents on Dou Dizhu with multiple processes.
  • doudizhu_random_process_pool.py:run random agents on Dou Dizhu with multiple processes using process pool.
  • leduc_holdem_cfr.py: train CFR on Leduc Hold'em.
  • leduc_holdem_dqn.py: train DQN on Leduc Hold'em.
  • leduc_holdem_dqn_pytorch.py: train DQN on Leduc Hold'em (pytorch implementation).
  • leduc_holdem_human.py: play against re-trained model on Leduc Hold'em.
  • leduc_holdem_nfsp.py: train NFSP on Leduc Hold'em.
  • leduc_holdem_nfsp_load_model.py: an example of loading pre-trained Leduc Hold'em model.
  • leduc_holdem_nfsp_load_model_2.py: another example of loading pre-trained Leduc Hold'em model with model zoo.
  • leduc_holdem_nfsp_pytorch.py: train NFSP on Leduc Hold'em (pytorch implementation).
  • leduc_holdem_nfsp_pytorch_load_model.py: an example of loading pre-trained Leduc Hold'em model (Pytorch).
  • leduc_holdem_nfsp_pytorch_load_model_2.py: another example of loading pre-trained Leduc Hold'em model with model zoo (Pytorch).
  • leduc_holdem_random.py: run random agents on Leduc Hold'em.
  • leduc_holdem_single.py: train DQN on Leduc Hold'em as single-agent environment.
  • limit_holdem_dqn.py: train DQN on Limit Texas Hold'em.
  • limit_holdem_nfsp.py: train NFSP on Limit Texas Hold'em.
  • limit_holdem_random.py: run random agents on Limit Texas Hold'em.
  • mahjong_dqn.py: train DQN on Mahjong.
  • mahjong_nfsp.py: train NFSP on Mahjong.
  • mahjong_random.py: run random agents on Mahjong.
  • nolimit_holdem_dqn.py: train DQN on No-Limit Texas Hold'em.
  • nolimit_holdem_nfsp.py: train NFSP on No-Limit Texas Hold'em.
  • nolimit_holdem_random.py: run random agents on No-Limit Gexas Hold'em.
  • simple_doudizhu_random.py: run random agents on Simple Dou Dizhu.
  • uno_dqn.py: train DQN on UNO.
  • uno_human.py: play against rule-based model on UNO.
  • uno_nfsp.py: train NFSP on UNO.
  • uno_random.py: run random agents on UNO.
  • uno_single.py: train DQN on UNO as single-agent environment.
  • Pretrained models: we put pre-trained models in /models. Refer to rlcard/models/pretrained_models.py