{"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/popgym-arcade-parallel-pixelated-pomdps","title":"POPGym Arcade: Parallel Pixelated POMDPs","arxiv_id":"2503.01450","date":"2025-03-03","proceeding":null,"authors":["Zekang Wang","Zhe He","Borong Zhang","Edan Toledo","Steven Morad"],"abstract":"We present the POPGym Arcade, a collection of hardware-accelerated, pixel-based environments with shared observation and action spaces. Each environment includes fully and partially observable variants, enabling counterfactual studies on partial observability. We also introduce mathematical tools for analyzing policies under partial observability, which reveal how agents recall past information to make decisions. Our analysis shows (1) that controlling for partial observability is critical and (2) that agents with long-term memory learn brittle policies that struggle to generalize. Finally, we demonstrate that recurrent policies can be \"poisoned\" by old, out-of-distribution observations, with implications for sim-to-real transfer, imitation learning, and offline reinforcement learning.","url_abs":"https://arxiv.org/abs/2503.01450v5","url_pdf":"https://arxiv.org/pdf/2503.01450v5.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":"popgym-arcade-parallel-pixelated-pomdps","repo_url":"https://github.com/bolt-research/popgym_arcade","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.01450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01450"}},"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/bolt-research/popgym_arcade","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"bda18ca4b1130374","entry":"debug_shape","repo":"bolt-research/popgym_arcade","repo_kind":"official","path":"popgym_arcade/baselines/dqn_rnn.py","file_url":"https://github.com/bolt-research/popgym_arcade/blob/HEAD/popgym_arcade/baselines/dqn_rnn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bda18ca4b1130374"}},{"code_sha256_prefix":"18638956ccc199d8","entry":"filter_scan","repo":"bolt-research/popgym_arcade","repo_kind":"official","path":"popgym_arcade/baselines/dqn.py","file_url":"https://github.com/bolt-research/popgym_arcade/blob/HEAD/popgym_arcade/baselines/dqn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18638956ccc199d8"}},{"code_sha256_prefix":"67aaa2797f6e7b1b","entry":"to_surf","repo":"bolt-research/popgym_arcade","repo_kind":"official","path":"popgym_arcade/play.py","file_url":"https://github.com/bolt-research/popgym_arcade/blob/HEAD/popgym_arcade/play.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67aaa2797f6e7b1b"}},{"code_sha256_prefix":"cdd00220e6d180e3","entry":"to_surf","repo":"bolt-research/popgym_arcade","repo_kind":"official","path":"popgym_arcade/play_both.py","file_url":"https://github.com/bolt-research/popgym_arcade/blob/HEAD/popgym_arcade/play_both.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cdd00220e6d180e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}