Gnimix
/

ppo

Reinforcement Learning

deep-reinforcement-learning

custom-implementation

Model card Files Files and versions

Metrics Training metrics Community

ppo / results.json

Gnimix's picture

Push Reinforce agent to the Hub

6b7dda2 over 2 years ago

173 Bytes

{"env_id": "LunarLander-v2", "mean_reward": -42.11552959973237, "std_reward": 20.505771574036753, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:35:26.402292"}