{"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/visualizing-and-understanding-atari-agents","title":"Visualizing and Understanding Atari Agents","arxiv_id":"1711.00138","date":"2017-10-31","proceeding":"ICML 2018 7","authors":["Sam Greydanus","Anurag Koul","Jonathan Dodge","Alan Fern"],"abstract":"While deep reinforcement learning (deep RL) agents are effective at\nmaximizing rewards, it is often unclear what strategies they use to do so. In\nthis paper, we take a step toward explaining deep RL agents through a case\nstudy using Atari 2600 environments. In particular, we focus on using saliency\nmaps to understand how an agent learns and executes a policy. We introduce a\nmethod for generating useful saliency maps and use it to show 1) what strong\nagents attend to, 2) whether agents are making decisions for the right or wrong\nreasons, and 3) how agents evolve during learning. We also test our method on\nnon-expert human subjects and find that it improves their ability to reason\nabout these agents. Overall, our results show that saliency information can\nprovide significant insight into an RL agent's decisions and learning behavior.","url_abs":"http://arxiv.org/abs/1711.00138v5","url_pdf":"http://arxiv.org/pdf/1711.00138v5.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":"visualizing-and-understanding-atari-agents","repo_url":"https://github.com/greydanus/visualize_atari","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"visualizing-and-understanding-atari-agents","repo_url":"https://github.com/KDL-umass/saliency_maps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"visualizing-and-understanding-atari-agents","repo_url":"https://github.com/slowjazz/interactive-atari-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.00138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00138"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/greydanus/visualize_atari","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/slowjazz/interactive-atari-RL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KDL-umass/saliency_maps","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"ef0d62e8fcceba28","entry":"get_mask","repo":"greydanus/visualize_atari","repo_kind":"official","path":"saliency.py","file_url":"https://github.com/greydanus/visualize_atari/blob/HEAD/saliency.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef0d62e8fcceba28"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}