0x05a4
/

DeepRL-PPO-LLv2

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

DeepRL-PPO-LLv2 / results.json

0x05a4

Baseline: LR=5e-4/cosine-100, epochs=1e7/305

ab2dd36 over 1 year ago

raw

history blame

157 Bytes

{"mean_reward": 288.9118304, "std_reward": 10.97332868779998, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-16T07:05:52.212687"}