a2c-PandaReachDense-v2-1 / results.json
Maxime Kuntz
Second training
6a1a930
raw
history blame contribute delete
165 Bytes
{"mean_reward": -1.0801521447021514, "std_reward": 0.529147232264188, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-26T22:15:29.280509"}