{"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/principled-exploration-via-optimistic","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","arxiv_id":"2105.06022","date":"2021-05-13","proceeding":null,"authors":["Chenjia Bai","Lingxiao Wang","Lei Han","Jianye Hao","Animesh Garg","Peng Liu","Zhaoran Wang"],"abstract":"One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with Deep Reinforcement Learning (DRL). In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I). OB2I constructs a general-purpose UCB-bonus through non-parametric bootstrap in DRL. The UCB-bonus estimates the epistemic uncertainty of state-action pairs for optimistic exploration. We build theoretical connections between the proposed UCB-bonus and the LSVI-UCB in a linear setting. We propagate future uncertainty in a time-consistent manner through episodic backward update, which exploits the theoretical advantage and empirically improves the sample-efficiency. Our experiments in the MNIST maze and Atari suite suggest that OB2I outperforms several state-of-the-art exploration approaches.","url_abs":"https://arxiv.org/abs/2105.06022v2","url_pdf":"https://arxiv.org/pdf/2105.06022v2.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":"principled-exploration-via-optimistic","repo_url":"https://github.com/Baichenjia/OB2I","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.06022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06022"}},"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/pokaxpoka/sunrise","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Kaixhin/Rainbow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Baichenjia/OB2I","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/johannah/bootstrap_dqn","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/rrmenon10/Bootstrapped-DQN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nikonikolov/rltf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/kazizzad/BDQN-MxNet-Gluon","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/review-anon/Bayesian-DQN","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"found_in_text":{"samples":10,"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":12,"samples":[{"code_sha256_prefix":"ab0fe214d7d0f41c","entry":"fixed_list_blobs","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/azure_utils.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/azure_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":false,"mcp_get_code":{"code_sha256":"ab0fe214d7d0f41c"}},{"code_sha256_prefix":"b7d6a34e1010c8d3","entry":"get_wrapper_by_name","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/misc_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/misc_util.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":false,"mcp_get_code":{"code_sha256":"b7d6a34e1010c8d3"}},{"code_sha256_prefix":"5908b0de70ae8316","entry":"linear_interpolation","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/schedules.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/schedules.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":false,"mcp_get_code":{"code_sha256":"5908b0de70ae8316"}},{"code_sha256_prefix":"d463e1295ed34b3c","entry":"make_output_format","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/logger.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/logger.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":false,"mcp_get_code":{"code_sha256":"d463e1295ed34b3c"}},{"code_sha256_prefix":"3dc7f82ede7de679","entry":"mean","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/tf_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/tf_util.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":false,"mcp_get_code":{"code_sha256":"3dc7f82ede7de679"}},{"code_sha256_prefix":"131bfcd55d2d25cc","entry":"pickle_load","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/misc_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/misc_util.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":false,"mcp_get_code":{"code_sha256":"131bfcd55d2d25cc"}},{"code_sha256_prefix":"accf0e50708b4878","entry":"pretty_eta","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/misc_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/misc_util.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":false,"mcp_get_code":{"code_sha256":"accf0e50708b4878"}},{"code_sha256_prefix":"ec87a50ac64b9e20","entry":"sum","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/tf_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/tf_util.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":false,"mcp_get_code":{"code_sha256":"ec87a50ac64b9e20"}},{"code_sha256_prefix":"9071c058ed8fc811","entry":"var","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/tf_util.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/tf_util.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":false,"mcp_get_code":{"code_sha256":"9071c058ed8fc811"}},{"code_sha256_prefix":"8da098180c1e95c9","entry":"wrap_atari_dqn","repo":"baichenjia/ob2i","repo_kind":"official","path":"run_atari.py","file_url":"https://github.com/baichenjia/ob2i/blob/HEAD/run_atari.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":"8da098180c1e95c9"}},{"code_sha256_prefix":"708d00bb3755539a","entry":"wrap_atari_evaluate_dqn","repo":"baichenjia/ob2i","repo_kind":"official","path":"run_atari.py","file_url":"https://github.com/baichenjia/ob2i/blob/HEAD/run_atari.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":"708d00bb3755539a"}},{"code_sha256_prefix":"bad6b483657393a5","entry":"wrap_dqn","repo":"rrmenon10/Bootstrapped-DQN","repo_kind":"found_in_text","path":"baselines/common/atari_wrappers_deprecated.py","file_url":"https://github.com/rrmenon10/Bootstrapped-DQN/blob/HEAD/baselines/common/atari_wrappers_deprecated.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":false,"mcp_get_code":{"code_sha256":"bad6b483657393a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}