epsil
/

dqn-LunarLander-v2

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

dqn-LunarLander-v2 / results.json

epsil

Upload DQN LunarLander-v2 trained agent

3a834c6 over 2 years ago

raw

history blame

163 Bytes

{"mean_reward": -112.74220731508103, "std_reward": 52.575250088335, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-04T15:36:01.285264"}