ppo-LunarLander-v2 / results.json
resosteen's picture
Complete unit 1 of the course by training the model on the LunarLander-v2 environment.
86fca79
raw
history blame
165 Bytes
{"mean_reward": 193.02770420205496, "std_reward": 105.06775360426049, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-13T15:54:03.060220"}