chirbard
/

ppo-BipedalWalker-v3

Reinforcement Learning

stable-baselines3

BipedalWalker-v3

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ppo-BipedalWalker-v3 / results.json

chirbard

Upload PPO BipedalWalker-v3 trained agent

4717b2e verified 7 months ago

raw

history blame

166 Bytes

{"mean_reward": -92.03958271462871, "std_reward": 0.09135166367737325, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-18T13:24:55.014812"}