zlicastro
/

zl-a2c-PandaReachDense-v2

Reinforcement Learning

stable-baselines3

PandaReachDense-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

zl-a2c-PandaReachDense-v2 / results.json

zlicastro

Initial training for PandaReachDense-v2

4c4a422 almost 2 years ago

raw

history blame

166 Bytes

{"mean_reward": -2.4681929713115096, "std_reward": 0.6572200322118653, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-07T03:08:01.384071"}