{"_id":"6aa520955bf664c9618f0442","id":"umesh251/ppo-LunarLander-v2-unit1","private":false,"pipeline_tag":"reinforcement-learning","library_name":"stable-baselines3","tags":["stable-baselines3","LunarLander-v2","deep-reinforcement-learning","reinforcement-learning","model-index","region:us"],"downloads":15,"likes":0,"modelId":"umesh251/ppo-LunarLander-v2-unit1","author":"umesh251","sha":"2eaee9f5386e81e643b0625626b3d6def6c3415f","lastModified":"2026-09-12T09:51:34.000Z","gated":false,"disabled":false,"model-index":[{"name":"PPO","results":[{"task":{"type":"reinforcement-learning","name":"reinforcement-learning"},"dataset":{"name":"LunarLander-v2","type":"LunarLander-v2"},"metrics":[{"type":"mean_reward","value":"269.67 +/- 18.78","name":"mean_reward","verified":false}]}]}],"config":{},"cardData":{"library_name":"stable-baselines3","tags":["LunarLander-v2","deep-reinforcement-learning","reinforcement-learning","stable-baselines3"],"model-index":[{"name":"PPO","results":[{"task":{"type":"reinforcement-learning","name":"reinforcement-learning"},"dataset":{"name":"LunarLander-v2","type":"LunarLander-v2"},"metrics":[{"type":"mean_reward","value":"269.67 +/- 18.78","name":"mean_reward","verified":false}]}]}]},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"ppo-LunarLander-v2.zip"},{"rfilename":"ppo-LunarLander-v2/_stable_baselines3_version"},{"rfilename":"ppo-LunarLander-v2/data"},{"rfilename":"ppo-LunarLander-v2/policy.optimizer.pth"},{"rfilename":"ppo-LunarLander-v2/policy.pth"},{"rfilename":"ppo-LunarLander-v2/pytorch_variables.pth"},{"rfilename":"ppo-LunarLander-v2/system_info.txt"},{"rfilename":"results.json"}],"spaces":[],"createdAt":"2026-09-12T09:51:17.000Z","usedStorage":284361}