DizzyDozze
/

study

Reinforcement Learning

stable-baselines3

SpaceInvadersNoFrameskip-v4

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

study / results.json

DizzyDozze

Initial commit

cf94612 7 months ago

raw

history blame

153 Bytes

{"mean_reward": 526.5, "std_reward": 46.639575469766015, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T08:25:41.578645"}