{"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/enabling-realtime-reinforcement-learning-at","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","arxiv_id":"2412.14355","date":"2024-12-18","proceeding":null,"authors":["Matthew Riemer","Gopeshh Subbaraj","Glen Berseth","Irina Rish"],"abstract":"Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pok\\'emon and Tetris.","url_abs":"https://arxiv.org/abs/2412.14355v1","url_pdf":"https://arxiv.org/pdf/2412.14355v1.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":"enabling-realtime-reinforcement-learning-at","repo_url":"https://github.com/cerc-aai/realtime_rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.14355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14355"}},"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/cerc-aai/realtime_rl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"cerc-aai/realtime_rl","repo_kind":"official","path":"simulate_delay_atari.py","file_url":"https://github.com/cerc-aai/realtime_rl/blob/HEAD/simulate_delay_atari.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"e8fe74ead30dde7c","entry":"same","repo":"cerc-aai/realtime_rl","repo_kind":"official","path":"environments/atari_env.py","file_url":"https://github.com/cerc-aai/realtime_rl/blob/HEAD/environments/atari_env.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":"e8fe74ead30dde7c"}},{"code_sha256_prefix":"a2742e3b27c99eb4","entry":"white","repo":"cerc-aai/realtime_rl","repo_kind":"official","path":"environments/atari_env.py","file_url":"https://github.com/cerc-aai/realtime_rl/blob/HEAD/environments/atari_env.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":"a2742e3b27c99eb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}