ppo-LunarLander-v2 / results.json
rstl
Deep rl model 1 mio steps
fec4cce
raw
history blame
165 Bytes
{"mean_reward": 282.19038524348497, "std_reward": 20.78524594516132, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-23T12:00:21.594524"}