3 Repos
Awesome GitHub RepositoriesRL Algorithm Benchmarking Toolkits
Toolkits for benchmarking reinforcement learning algorithms like DQN, NFSP, and CFR across standardized tasks.
Distinct from Algorithm Benchmarking Libraries: Distinct from Algorithm Benchmarking Libraries: focuses on RL-specific algorithms and standardized card game tasks, not general algorithm benchmarking.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · RL Algorithm Benchmarking Toolkits. Refine with filters or upvote what's useful.
Awesome RL Algorithm Benchmarking Toolkits GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- google-deepmind/acme
google-deepmind/acme
4,005Auf GitHub ansehenAcme ist ein Framework für Reinforcement Learning und eine Ausführungsumgebung, die für die Entwicklung und das Benchmarking von Lernalgorithmen konzipiert wurde. Es bietet eine Bibliothek modularer Komponenten und Referenzimplementierungen, mit denen Agenten erstellt und Performance-Baselines etabliert werden können. Das System ermöglicht die Skalierung von Agenten-Architekturen von der Single-Stream-Ausführung bis hin zu großen verteilten Umgebungen. Dies erlaubt den Übergang vom ersten Prototyping zur verteilten Ausführung für Training und Evaluierung. Das Framework deckt die Entwicklung von Reinforcement Learning und das Prototyping von Agenten-Architekturen ab und liefert die notwendigen Bausteine, um neue Modelle gegen Standard-Referenzagenten zu benchen.
Implements toolkits for benchmarking new reinforcement learning algorithms against standard reference agents.
Python - datamllab/rlcard
datamllab/rlcard
3,401Auf GitHub ansehenRLcard 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
A toolkit for benchmarking reinforcement learning algorithms like DQN, NFSP, and CFR across standardized card game tasks.
Pythonaiblackjackcard-game - dlr-rm/rl-baselines3-zoo
DLR-RM/rl-baselines3-zoo
2,725Auf GitHub ansehenThis project is a collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3 and Gymnasium. It provides a framework for training agents to solve specific tasks, managing experiment reproducibility, and deploying pretrained models. The system includes a specialized benchmarking suite and optimization tools for tuning agent settings. It utilizes automated search spaces and distributed trials to maximize performance, while employing bootstrap sampling to generate statistically robust performance metrics and confidence intervals. Broad capabilities cov
Ships a specialized benchmarking suite for evaluating RL agent success using statistically robust metrics.
Pythondeep-reinforcement-learninggymhyperparameter-optimization
