{"id":"2506.06323","title":"Composite Reward Design in PPO-Driven Adaptive Filtering","url":"https://codeofpaper.com/paper/2506.06323","arxiv_url":"https://arxiv.org/abs/2506.06323","published":"2025-05-29","code":"community","best":{"full_name":"Bradshard/Reinforcement_Learning","url":"https://github.com/Bradshard/Reinforcement_Learning","tier":"high_confidence_community","stars":1,"license":null,"framework":null,"language":"Python","last_commit":"2026-04-09T08:54:47"},"most_starred_community":null,"implementations":[{"full_name":"Bradshard/Reinforcement_Learning","url":"https://github.com/Bradshard/Reinforcement_Learning","tier":"high_confidence_community","stars":1,"license":null,"framework":null,"language":"Python","last_commit":"2026-04-09T08:54:47"}],"possible_matches":0}