{"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/hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","arxiv_id":"2402.10228","date":"2024-02-05","proceeding":null,"authors":["Yingru Li","Jiawei Xu","Lei Han","Zhi-Quan Luo"],"abstract":"We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\\star$) without the need for conjugacy and follows the greedy policies w.r.t. these approximate posterior samples. We demonstrate that HyperAgent offers robust performance in large-scale deep RL benchmarks. It can solve Deep Sea hard exploration problems with episodes that optimally scale with problem size and exhibits significant efficiency gains in the Atari suite. Implementing HyperAgent requires minimal code addition to well-established deep RL frameworks like DQN. We theoretically prove that, under tabular assumptions, HyperAgent achieves logarithmic per-step computational complexity while attaining sublinear regret, matching the best known randomized tabular RL algorithm.","url_abs":"https://arxiv.org/abs/2402.10228v5","url_pdf":"https://arxiv.org/pdf/2402.10228v5.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":"hyperagent-a-simple-scalable-efficient-and","repo_url":"https://github.com/szrlee/hyperagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hyperagent-a-simple-scalable-efficient-and","repo_url":"https://github.com/szrlee/GPT-HyperAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hyperagent-a-simple-scalable-efficient-and","repo_url":"https://github.com/szrlee/ensemble_plus_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"atari-games-100k","task_name":"Atari Games 100k"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"lemma","task_name":"LEMMA"},{"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":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.10228","atlas_url":"https://app.syntology.ai/?focus=2402.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10228"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/szrlee/GPT-HyperAgent","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/szrlee/hyperagent","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/szrlee/ensemble_plus_plus","reach":null}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"7987a0deae85f58b","entry":"make_env","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/env/utils.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7987a0deae85f58b"}},{"code_sha256_prefix":"ced646fc0c60b73a","entry":"miniblock","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/network/common.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/network/common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ced646fc0c60b73a"}},{"code_sha256_prefix":"6d1e49fae9c78bff","entry":"rd_argmax","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/policy/hyper_utils.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/policy/hyper_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d1e49fae9c78bff"}},{"code_sha256_prefix":"cedd0815975bd1b5","entry":"make_atari_env","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/env/utils.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/utils.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":"cedd0815975bd1b5"}},{"code_sha256_prefix":"06b74e86dd4dc4da","entry":"make_atari_env_watch","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/env/utils.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/utils.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":"06b74e86dd4dc4da"}},{"code_sha256_prefix":"ebe5258db5d557d3","entry":"wrap_atari","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/env/atari_wrapper.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/atari_wrapper.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":"ebe5258db5d557d3"}},{"code_sha256_prefix":"f407a5134f319b52","entry":"wrap_deepmind","repo":"szrlee/hyperagent","repo_kind":"official","path":"hyperagent/env/atari_wrapper.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/atari_wrapper.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":"f407a5134f319b52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}