SatCat
/

a2c-PandaReachDense-v2

Reinforcement Learning

stable-baselines3

PandaReachDense-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

a2c-PandaReachDense-v2 / results.json

SatCat

Total-1M4-train-steps commit

9d1e3de almost 2 years ago

raw

history blame

167 Bytes

{"mean_reward": -0.4441687039434328, "std_reward": 0.15308496516446732, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-19T05:14:01.636201"}