robotman0
/

unit1-ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

unit1-ppo-LunarLander-v2 / results.json

robotman0

default params for 1 million timesteps. reposted

9150183 over 1 year ago

raw

history blame

164 Bytes

{"mean_reward": 277.0569745650478, "std_reward": 16.931117815677535, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T18:22:54.319212"}