{"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/beyond-the-rainbow-high-performance-deep","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","arxiv_id":"2411.03820","date":"2024-11-06","proceeding":null,"authors":["Tyler Clark","Mark Towers","Christine Evers","Jonathon Hare"],"abstract":"Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present \"Beyond The Rainbow\" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on Atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a high-end desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analyzing the performance and impact using numerous measures. Code is available at https://github.com/VIPTankz/BTR.","url_abs":"https://arxiv.org/abs/2411.03820v2","url_pdf":"https://arxiv.org/pdf/2411.03820v2.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":"beyond-the-rainbow-high-performance-deep","repo_url":"https://github.com/viptankz/btr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-the-rainbow-high-performance-deep","repo_url":"https://github.com/rickyegl/BeyondTheRainbowICLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"beyond-the-rainbow-high-performance-deep","repo_url":"https://github.com/rickyegl/BeyondTheRainbowM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"dueling-network","method_name":"Dueling Network"},{"method_slug":"n-step-returns","method_name":"N-step Returns"},{"method_slug":"noisy-net","method_name":"Noisy Linear Layer"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"rainbow-dqn","method_name":"Rainbow DQN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.03820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03820"}},"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":"deterministic:regex_extraction","url":"https://github.com/VIPTankz/BTR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/viptankz/btr","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rickyegl/BeyondTheRainbowM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rickyegl/BeyondTheRainbowICLR","reach":null}],"summary":{"ran":10,"ran_draft_wrong":3,"unverified":12},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":21,"ran":13,"repositories":2}},"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":21,"samples":[{"code_sha256_prefix":"ebfa2628b0000e65","entry":"Analytics","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ebfa2628b0000e65"}},{"code_sha256_prefix":"bacc2cddb664bea4","entry":"Dueling","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bacc2cddb664bea4"}},{"code_sha256_prefix":"17e8fcddd3188058","entry":"EpsilonGreedy","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"17e8fcddd3188058"}},{"code_sha256_prefix":"4d142f883464d0f9","entry":"FactorizedNoisyLinear","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d142f883464d0f9"}},{"code_sha256_prefix":"888002b8a86e5a03","entry":"ImpalaCNNBlock","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"888002b8a86e5a03"}},{"code_sha256_prefix":"e9e1b699914b69e5","entry":"ImpalaCNNLargeC51","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e9e1b699914b69e5"}},{"code_sha256_prefix":"41b0ef198d33a0be","entry":"ImpalaCNNResidual","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41b0ef198d33a0be"}},{"code_sha256_prefix":"9e6f2536b7248907","entry":"NoisyLinear","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e6f2536b7248907"}},{"code_sha256_prefix":"5cbd6045f5cc87d7","entry":"PER","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5cbd6045f5cc87d7"}},{"code_sha256_prefix":"20c72900e5bac6d6","entry":"SumTree","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20c72900e5bac6d6"}},{"code_sha256_prefix":"7c1d5bc9f897b0cf","entry":"calculate_huber_loss","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7c1d5bc9f897b0cf"}},{"code_sha256_prefix":"8f1b5f746f353929","entry":"distr_projection","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f1b5f746f353929"}},{"code_sha256_prefix":"421450b8959b8fd6","entry":"randomise_action_batch","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"421450b8959b8fd6"}},{"code_sha256_prefix":"286da1c5eb5d8dde","entry":"Agent","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"286da1c5eb5d8dde"}},{"code_sha256_prefix":"45091c96548faa63","entry":"Agent","repo":"rickyegl/BeyondTheRainbowM","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowM/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45091c96548faa63"}},{"code_sha256_prefix":"5b8f960bf199e9b6","entry":"ImpalaCNNLarge","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b8f960bf199e9b6"}},{"code_sha256_prefix":"2fda2e0b0dc97a26","entry":"ImpalaCNNLargeIQN","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fda2e0b0dc97a26"}},{"code_sha256_prefix":"63f4b89e2f29bee0","entry":"ImpalaCNNLargeIQN","repo":"rickyegl/BeyondTheRainbowM","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowM/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63f4b89e2f29bee0"}},{"code_sha256_prefix":"adf5a79486613798","entry":"NatureIQN","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"adf5a79486613798"}},{"code_sha256_prefix":"5702ceae0fbebc7b","entry":"choose_eval_action","repo":"VIPTankz/BTR","repo_kind":"official","path":"Agent.py","file_url":"https://github.com/VIPTankz/BTR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","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":"5702ceae0fbebc7b"}},{"code_sha256_prefix":"b7f6c4806f2bb9ff","entry":"create_experience","repo":"VIPTankz/BTR","repo_kind":"official","path":"PER.py","file_url":"https://github.com/VIPTankz/BTR/blob/HEAD/PER.py","link_basis":"first_harvest_node","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":"b7f6c4806f2bb9ff"}},{"code_sha256_prefix":"0a3ccb7803118980","entry":"create_network","repo":"rickyegl/BeyondTheRainbowICLR","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a3ccb7803118980"}},{"code_sha256_prefix":"de954c232508133f","entry":"create_network","repo":"rickyegl/BeyondTheRainbowM","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowM/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de954c232508133f"}},{"code_sha256_prefix":"b47df527aff11259","entry":"moving_average","repo":"VIPTankz/BTR","repo_kind":"official","path":"Analytic.py","file_url":"https://github.com/VIPTankz/BTR/blob/HEAD/Analytic.py","link_basis":"first_harvest_node","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":"b47df527aff11259"}},{"code_sha256_prefix":"48242805f8b06f3a","entry":"randomise_action_batch","repo":"VIPTankz/BTR","repo_kind":"official","path":"Agent.py","file_url":"https://github.com/VIPTankz/BTR/blob/HEAD/Agent.py","link_basis":"first_harvest_node","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":"48242805f8b06f3a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}