{"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/learning-time-sensitive-strategies-in-space","title":"Learning Time-Sensitive Strategies in Space Fortress","arxiv_id":"1805.06824","date":"2018-05-17","proceeding":null,"authors":["Akshat Agarwal","Ryan Hope","Katia Sycara"],"abstract":"Although there has been remarkable progress and impressive performance on\nreinforcement learning (RL) on Atari games, there are many problems with\nchallenging characteristics that have not yet been explored in Deep Learning\nfor RL. These include reward sparsity, abrupt context-dependent reversals of\nstrategy and time-sensitive game play. In this paper, we present Space\nFortress, a game that incorporates all these characteristics and experimentally\nshow that the presence of any of these renders state of the art Deep RL\nalgorithms incapable of learning. Then, we present our enhancements to an\nexisting algorithm and show big performance increases through each enhancement\nthrough an ablation study. We discuss how each of these enhancements was able\nto help and also argue that appropriate transfer learning boosts performance.","url_abs":"http://arxiv.org/abs/1805.06824v4","url_pdf":"http://arxiv.org/pdf/1805.06824v4.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":"learning-time-sensitive-strategies-in-space","repo_url":"https://github.com/agakshat/spacefortress","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"Space Fortress"},{"task_slug":"transfer-learning","task_name":"Transfer 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}