{"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/latent-world-models-for-intrinsically","title":"Latent World Models For Intrinsically Motivated Exploration","arxiv_id":"2010.02302","date":"2020-10-05","proceeding":"NeurIPS 2020 12","authors":["Aleksandr Ermolov","Nicu Sebe"],"abstract":"In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arranges embeddings respecting temporal distance of observations. This representation is empirically robust to stochasticity and suitable for novelty detection from the error of a predictive forward model. We consider episodic and life-long uncertainties to guide the exploration. We propose to estimate the missing information about the environment with the world model, which operates in the learned latent space. As a motivation of the method, we analyse the exploration problem in a tabular Partially Observable Labyrinth. We demonstrate the method on image-based hard exploration environments from the Atari benchmark and report significant improvement with respect to prior work. The source code of the method and all the experiments is available at https://github.com/htdt/lwm.","url_abs":"https://arxiv.org/abs/2010.02302v1","url_pdf":"https://arxiv.org/pdf/2010.02302v1.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":"latent-world-models-for-intrinsically","repo_url":"https://github.com/htdt/lwm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.02302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02302"}},"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/htdt/lwm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"281bb05003cb181b","entry":"get_td_error","repo":"htdt/lwm","repo_kind":"official","path":"pol/dqn/algo.py","file_url":"https://github.com/htdt/lwm/blob/HEAD/pol/dqn/algo.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":"281bb05003cb181b"}},{"code_sha256_prefix":"e747edf4bce70cf1","entry":"inv_vf_rescaling","repo":"htdt/lwm","repo_kind":"official","path":"atari/dqn/algo.py","file_url":"https://github.com/htdt/lwm/blob/HEAD/atari/dqn/algo.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":"e747edf4bce70cf1"}},{"code_sha256_prefix":"f83b216707ff2af0","entry":"mnih_cnn","repo":"htdt/lwm","repo_kind":"official","path":"atari/dqn/model.py","file_url":"https://github.com/htdt/lwm/blob/HEAD/atari/dqn/model.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":"f83b216707ff2af0"}},{"code_sha256_prefix":"982a7d72335949fd","entry":"step_grid","repo":"htdt/lwm","repo_kind":"official","path":"pol/pol_env.py","file_url":"https://github.com/htdt/lwm/blob/HEAD/pol/pol_env.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":"982a7d72335949fd"}},{"code_sha256_prefix":"fe86ad79d86af207","entry":"vf_rescaling","repo":"htdt/lwm","repo_kind":"official","path":"atari/dqn/algo.py","file_url":"https://github.com/htdt/lwm/blob/HEAD/atari/dqn/algo.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":"fe86ad79d86af207"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}