EdithKim
/

a2c

Reinforcement Learning

stable-baselines3

PandaReachDense-v3

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

a2c / results.json

EdithKim

initial commit

fc8614f 12 months ago

raw

history blame

168 Bytes

{"mean_reward": -0.18391927843913436, "std_reward": 0.09886629047145956, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T06:28:42.001623"}