AIbase
ProduktbibliothekTool Navigation

CartPole-Reinforcement-Learning

Public

Uses the Stable Baselines 3 and OpenAI Python libraries to train models that attempt to solve the CartPole problem using 3 reinforcement learning algorithms; PPO (Proximal Policy Optimization), A2C (Advantage Actor Critic) and DQN (Deep Q Learning).

Erstellungszeit2022-04-25T05:46:56
Aktualisierungszeit2023-06-04T05:49:10
1
Stars
0
Stars Increase

Verwandte Projekte