enaitzb
/

a2c-PandaReach-v3

Reinforcement Learning

stable-baselines3

PandaReach-v3

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

a2c-PandaReach-v3 / results.json

enaitzb

Initial commit

976d5a9 about 1 year ago

raw

history blame

151 Bytes

{"mean_reward": -2.2, "std_reward": 0.9797958971132713, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-04T07:41:03.698927"}