wywang
/

ppo-LunarLander-v2-trained-with-wind-env

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ppo-LunarLander-v2-trained-with-wind-env / results.json

wywang

[Deep RL Unit 1] Trained agent for LunarLander-v2, trained with wind, evaluated without wind

454c745 verified 4 months ago

raw history blame contribute delete

No virus

165 Bytes

{"mean_reward": 203.02327140000003, "std_reward": 112.78014201670442, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T16:43:17.416657"}