sky-2002
/

aakash-ppo-lunar-lander-v2-try_3

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

aakash-ppo-lunar-lander-v2-try_3 / results.json

sky-2002

Push more trained(2000000 iterations) LunarLander-v2 model

d3b7b7b about 2 years ago

raw

history blame

164 Bytes

{"mean_reward": 245.9597477278499, "std_reward": 19.806736417966547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T07:19:55.996338"}