{"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/cobra-data-efficient-model-based-rl-through","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","arxiv_id":"1905.09275","date":"2019-05-22","proceeding":null,"authors":["Nicholas Watters","Loic Matthey","Matko Bosnjak","Christopher P. Burgess","Alexander Lerchner"],"abstract":"Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.","url_abs":"https://arxiv.org/abs/1905.09275v2","url_pdf":"https://arxiv.org/pdf/1905.09275v2.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":"cobra-data-efficient-model-based-rl-through","repo_url":"https://github.com/deepmind/spriteworld","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cobra-data-efficient-model-based-rl-through","repo_url":"https://github.com/google-deepmind/spriteworld","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.09275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09275"}},"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/google-deepmind/spriteworld","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/spriteworld","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"e54f1b19d2bbef8d","entry":"hsv_to_rgb","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/renderers/color_maps.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/renderers/color_maps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e54f1b19d2bbef8d"}},{"code_sha256_prefix":"ba62f1bcd49200d5","entry":"polygon","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/shapes.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/shapes.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba62f1bcd49200d5"}},{"code_sha256_prefix":"0fb6b30eedcac7ac","entry":"sample_generator","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/sprite_generators.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/sprite_generators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0fb6b30eedcac7ac"}},{"code_sha256_prefix":"5af55bc5d9e1b38d","entry":"shuffle","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/sprite_generators.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/sprite_generators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5af55bc5d9e1b38d"}},{"code_sha256_prefix":"4b016f2165ba807b","entry":"spokes","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/shapes.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/shapes.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b016f2165ba807b"}},{"code_sha256_prefix":"1e3c9dfb2fdc11e8","entry":"star","repo":"deepmind/spriteworld","repo_kind":"official","path":"spriteworld/shapes.py","file_url":"https://github.com/deepmind/spriteworld/blob/HEAD/spriteworld/shapes.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e3c9dfb2fdc11e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}