robotman0
/

ppo-LunarLander-v2

Reinforcement Learning

deep-reinforcement-learning

custom-implementation

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ppo-LunarLander-v2 / results.json

robotman0's picture

default params for 1 million timesteps

d0f75d7 almost 2 years ago

164 Bytes

{"mean_reward": 267.8647628564487, "std_reward": 17.007886560335173, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T19:23:59.736682"}