{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/amplifying-the-imitation-effect-for","title":"Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution","arxiv_id":"1901.05856","date":"2019-01-17","proceeding":null,"authors":["Gyeong Taek Lee","Chang Ouk Kim"],"abstract":"This paper proposes a new reinforcement learning (RL) algorithm that enhances\nexploration by amplifying the imitation effect (AIE). This algorithm consists\nof self-imitation learning and random network distillation algorithms. We argue\nthat these two algorithms complement each other and that combining these two\nalgorithms can amplify the imitation effect for exploration. In addition, by\nadding an intrinsic penalty reward to the state that the RL agent frequently\nvisits and using replay memory for learning the feature state when using an\nexploration bonus, the proposed approach leads to deep exploration and deviates\nfrom the current converged policy. We verified the exploration performance of\nthe algorithm through experiments in a two-dimensional grid environment. In\naddition, we applied the algorithm to a simulated environment of unmanned\ncombat aerial vehicle (UCAV) mission execution, and the empirical results show\nthat AIE is very effective for finding the UCAV's shortest flight path to avoid\nan enemy's missiles.","url_abs":"http://arxiv.org/abs/1901.05856v1","url_pdf":"http://arxiv.org/pdf/1901.05856v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"amplifying-the-imitation-effect-for","repo_url":"https://github.com/cejuicreamice/R_easy_RL_fix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}