policy
PPO-Agent-with-Generative-Modeling-in-Leduc-Poker
kailiu0712 · PyTorch
or hover any field below to flag it
Overview
Name
PPO-Agent-with-Generative-Modeling-in-Leduc-Poker
Author
kailiu0712
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Used a generative neural network as opponent model in Reinforcement Learning to improve PPO agent's performance in heads-up Leduc poker. The opponent predictor is trained synchronically along with the policy and value networks. 2-stage training with random opponent and self-play. Successfully increa
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list PPO-Agent-with-Generative-Modeling-in-Leduc-Poker yet.
Datasets that reference this policy
0No datasets reference PPO-Agent-with-Generative-Modeling-in-Leduc-Poker yet.