whirlie
/

a2c-01

Reinforcement Learning

stable-baselines3

PandaReachDense-v3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

xet

Community

a2c-01 / results.json

whirlie

Initial commit

853f128 verified 12 months ago

raw

history blame contribute delete

168 Bytes

{"mean_reward": -0.22535187639296056, "std_reward": 0.11719899077208513, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-10T09:48:18.221116"}