{"id":"2410.13837","title":"ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization","url":"https://codeofpaper.com/paper/2410.13837","arxiv_url":"https://arxiv.org/abs/2410.13837","published":"2024-10-17","code":"community","best":{"full_name":"calvincbzhang/orso","url":"https://github.com/calvincbzhang/orso","tier":"high_confidence_community","stars":2,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-10-18T03:01:10"},"most_starred_community":null,"implementations":[{"full_name":"calvincbzhang/orso","url":"https://github.com/calvincbzhang/orso","tier":"high_confidence_community","stars":2,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-10-18T03:01:10"}],"possible_matches":1}