{"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/width-based-planning-and-active-learning-for","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","arxiv_id":"2109.15310","date":"2021-09-30","proceeding":null,"authors":["Benjamin Ayton","Masataro Asai"],"abstract":"Width-based planning has shown promising results on Atari 2600 games using pixel input, while using substantially fewer environment interactions than reinforcement learning. Recent width-based approaches have computed feature vectors for each screen using a hand designed feature set or a variational autoencoder trained on game screens (VAE-IW), and prune screens that do not have novel features during the search. We propose Olive (Online-VAE-IW), which updates the VAE features online using active learning to maximize the utility of screens observed during planning. Experimental results in 55 Atari games demonstrate that it outperforms Rollout-IW by 42-to-11 and VAE-IW by 32-to-20. Moreover, Olive outperforms existing work based on policy-learning ($\\pi$-IW, DQN) trained with 100x training budget by 30-to-22 and 31-to-17, and a state of the art data-efficient reinforcement learning (EfficientZero) trained with the same training budget and ran with 1.8x planning budget by 18-to-7 in Atari 100k benchmark, with no policy learning at all. The source code is available at github.com/ibm/atari-active-learning .","url_abs":"https://arxiv.org/abs/2109.15310v2","url_pdf":"https://arxiv.org/pdf/2109.15310v2.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":"width-based-planning-and-active-learning-for","repo_url":"https://github.com/ibm/atari-active-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.15310","atlas_url":"https://app.syntology.ai/?focus=2109.15310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15310"}},"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/ibm/atari-active-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"e42930998c750683","entry":"create_data_loaders","repo":"ibm/atari-active-learning","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"e42930998c750683"}},{"code_sha256_prefix":"eddc64064f4b1c5b","entry":"create_test_dataset","repo":"ibm/atari-active-learning","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"eddc64064f4b1c5b"}},{"code_sha256_prefix":"27bbcdf74d4cdba3","entry":"ensure_list","repo":"ibm/atari-active-learning","repo_kind":"official","path":"aggregate_pandas.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/aggregate_pandas.py","link_basis":"harvester_set","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":"27bbcdf74d4cdba3"}},{"code_sha256_prefix":"2034f222774b1d7f","entry":"entropy","repo":"ibm/atari-active-learning","repo_kind":"official","path":"active_learning_screen.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/active_learning_screen.py","link_basis":"harvester_set","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":"2034f222774b1d7f"}},{"code_sha256_prefix":"77b2a210d19e78df","entry":"fn2","repo":"ibm/atari-active-learning","repo_kind":"official","path":"stacktrace.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/stacktrace.py","link_basis":"harvester_set","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":"77b2a210d19e78df"}},{"code_sha256_prefix":"87faa0ad6e55f861","entry":"number_has_leading_zeros_p","repo":"ibm/atari-active-learning","repo_kind":"official","path":"printing_util.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/printing_util.py","link_basis":"harvester_set","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":"87faa0ad6e55f861"}},{"code_sha256_prefix":"8e50712b6aa876b2","entry":"read_json","repo":"ibm/atari-active-learning","repo_kind":"official","path":"aggregate_pandas.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/aggregate_pandas.py","link_basis":"harvester_set","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":"8e50712b6aa876b2"}},{"code_sha256_prefix":"cb7a648af304657f","entry":"load_results","repo":"ibm/atari-active-learning","repo_kind":"official","path":"aggregate_pandas.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/aggregate_pandas.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":"cb7a648af304657f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}