{"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/q-map-a-convolutional-approach-for-goal","title":"Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks","arxiv_id":"1810.02927","date":"2018-10-06","proceeding":"ICLR 2019 5","authors":["Fabio Pardo","Vitaly Levdik","Petar Kormushev"],"abstract":"Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallel limited the approach to small tabular cases so far. To tackle this problem we propose to use convolutional network architectures to generate Q-values and updates for a large number of goals at once. We demonstrate the accuracy and generalization qualities of the proposed method on randomly generated mazes and Sokoban puzzles. In the case of on-screen goal coordinates the resulting mapping from frames to distance-maps directly informs the agent about which places are reachable and in how many steps. As an example of application we show that replacing the random actions in epsilon-greedy exploration by several actions towards feasible goals generates better exploratory trajectories on Montezuma's Revenge and Super Mario All-Stars games.","url_abs":"https://arxiv.org/abs/1810.02927v2","url_pdf":"https://arxiv.org/pdf/1810.02927v2.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":"q-map-a-convolutional-approach-for-goal","repo_url":"https://github.com/fabiopardo/qmap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"q-map-a-convolutional-approach-for-goal","repo_url":"https://github.com/yl3829/Q-map","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"snes-games","task_name":"SNES Games"},{"task_slug":"sokoban","task_name":"Sokoban"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.02927","atlas_url":"https://app.syntology.ai/?focus=1810.02927","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}