1 Repo
Pluggable RL algorithms that operate on a standardized environment interface without modifying game logic.
Distinct from Pluggable Architectures: Distinct from Pluggable Architectures: specifically for reinforcement learning algorithms like DQN, NFSP, and CFR, not general pluggable patterns.
Explore 1 awesome GitHub repository matching data & databases · Reinforcement Learning Algorithm Plugins. Refine with filters or upvote what's useful.
RLcard is an open-source framework for developing and evaluating reinforcement learning agents across multiple card game environments. It functions as a card game environment simulator, a multi-agent RL platform, and a benchmarking toolkit for algorithms like DQN, NFSP, and CFR. The framework provides a game-agnostic environment interface that decouples agent logic from game mechanics, allowing any policy to interact through a common API. It supports pluggable reinforcement learning algorithms that operate on this interface without modifying game logic, and includes a self-play training loop
Supports pluggable RL algorithms (DQN, NFSP, DMC, CFR) that operate on the environment interface without modifying game logic.