alexbalandi
/

ppo-LunarLander-v2-4milsteps-200-envs

Reinforcement Learning

stable-baselines3

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ppo-LunarLander-v2-4milsteps-200-envs / results.json

alexbalandi

Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.

3120398 almost 2 years ago

raw

history blame

163 Bytes

{"mean_reward": 286.0182618528187, "std_reward": 16.23159898013778, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-13T10:49:57.212941"}