dn-gh
/

TQC-PandaReachDense-v2

Reinforcement Learning

stable-baselines3

PandaReachDense-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

TQC-PandaReachDense-v2 / results.json

dn-gh

Initial commit

28aa1bb almost 2 years ago

raw

history blame

168 Bytes

{"mean_reward": -0.20964387570566032, "std_reward": 0.10604512722828112, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-08T01:04:55.027289"}