{"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/hieros-hierarchical-imagination-on-structured","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","arxiv_id":"2310.05167","date":"2023-10-08","proceeding":null,"authors":["Paul Mattes","Rainer Schlosser","Ralf Herbrich"],"abstract":"One of the biggest challenges to modern deep reinforcement learning (DRL) algorithms is sample efficiency. Many approaches learn a world model in order to train an agent entirely in imagination, eliminating the need for direct environment interaction during training. However, these methods often suffer from either a lack of imagination accuracy, exploration capabilities, or runtime efficiency. We propose Hieros, a hierarchical policy that learns time abstracted world representations and imagines trajectories at multiple time scales in latent space. Hieros uses an S5 layer-based world model, which predicts next world states in parallel during training and iteratively during environment interaction. Due to the special properties of S5 layers, our method can train in parallel and predict next world states iteratively during imagination. This allows for more efficient training than RNN-based world models and more efficient imagination than Transformer-based world models. We show that our approach outperforms the state of the art in terms of mean and median normalized human score on the Atari 100k benchmark, and that our proposed world model is able to predict complex dynamics very accurately. We also show that Hieros displays superior exploration capabilities compared to existing approaches.","url_abs":"https://arxiv.org/abs/2310.05167v3","url_pdf":"https://arxiv.org/pdf/2310.05167v3.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":"hieros-hierarchical-imagination-on-structured","repo_url":"https://github.com/snagnar/hieros","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.05167","atlas_url":"https://app.syntology.ai/?focus=2310.05167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05167"}},"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":"deterministic:regex_extraction","url":"https://github.com/Snagnar/Hieros","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snagnar/hieros","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"a044c344102c93c6","entry":"binary_operator","repo":"Snagnar/Hieros","repo_kind":"official","path":"resettable_s5/s5_model.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/resettable_s5/s5_model.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":"a044c344102c93c6"}},{"code_sha256_prefix":"adab19312b0e91d3","entry":"convert","repo":"Snagnar/Hieros","repo_kind":"official","path":"embodied/core/basics.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/embodied/core/basics.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":"adab19312b0e91d3"}},{"code_sha256_prefix":"b7ff9ef9697d35f1","entry":"count_steps","repo":"Snagnar/Hieros","repo_kind":"official","path":"hieros/dreamer.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/hieros/dreamer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7ff9ef9697d35f1"}},{"code_sha256_prefix":"0443d69d357e19c2","entry":"expand","repo":"Snagnar/Hieros","repo_kind":"official","path":"hieros/dreamer.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/hieros/dreamer.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":"0443d69d357e19c2"}},{"code_sha256_prefix":"0efcf0eccfce4e62","entry":"resettable_binary_operator","repo":"Snagnar/Hieros","repo_kind":"official","path":"resettable_s5/s5_model.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/resettable_s5/s5_model.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":"0efcf0eccfce4e62"}},{"code_sha256_prefix":"96c396be6ac95ca0","entry":"smooth_values","repo":"Snagnar/Hieros","repo_kind":"official","path":"sampler_visualization.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/sampler_visualization.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":"96c396be6ac95ca0"}},{"code_sha256_prefix":"fd421307a7e4cede","entry":"symexp","repo":"Snagnar/Hieros","repo_kind":"official","path":"hieros/tools.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/hieros/tools.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd421307a7e4cede"}},{"code_sha256_prefix":"3e346b9b00ea8169","entry":"symlog","repo":"Snagnar/Hieros","repo_kind":"official","path":"hieros/tools.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/hieros/tools.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e346b9b00ea8169"}},{"code_sha256_prefix":"f1bc3f3f582c039d","entry":"apply_resettable_ssm","repo":"Snagnar/Hieros","repo_kind":"official","path":"resettable_s5/s5_model.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/resettable_s5/s5_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":"f1bc3f3f582c039d"}},{"code_sha256_prefix":"3360b32511bc42d4","entry":"format_","repo":"Snagnar/Hieros","repo_kind":"official","path":"embodied/core/basics.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/embodied/core/basics.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":"3360b32511bc42d4"}},{"code_sha256_prefix":"5ba274a4e18b46f3","entry":"treemap","repo":"Snagnar/Hieros","repo_kind":"official","path":"embodied/core/basics.py","file_url":"https://github.com/Snagnar/Hieros/blob/HEAD/embodied/core/basics.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":"5ba274a4e18b46f3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}