ppo-LunarLander-v2-tuned / results.json
tjscollins's picture
Model after coordinate descent hyperparameter search
932b701
raw
history blame contribute delete
No virus
164 Bytes
{"mean_reward": 292.6712552872903, "std_reward": 15.300508011802128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T01:11:31.173606"}