a2c-PandaReachDense-v2 / results.json
VAZaytsev's picture
New training parameters
50236b8
{"mean_reward": -0.8756055674282834, "std_reward": 0.24434654347595558, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-07T14:20:46.330708"}