{"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/in-a-nutshell-the-human-asked-for-this-latent-1","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","arxiv_id":"2110.09461","date":"2021-10-18","proceeding":"ICLR 2022 4","authors":["Borja G. León","Murray Shanahan","Francesco Belardinelli"],"abstract":"We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the agent's neural architecture is a key feature when DRL agents are learning to solve OOD tasks in TL. Yet, the studies on this topic are still in their infancy. In this work, we propose a new deep learning configuration with inductive biases that lead agents to generate latent representations of their current goal, yielding a stronger generalization performance. We use these latent-goal networks within a neuro-symbolic framework that executes multi-task formally-defined instructions and contrast the performance of the proposed neural networks against employing different state-of-the-art (SOTA) architectures when generalizing to unseen instructions in OOD environments.","url_abs":"https://arxiv.org/abs/2110.09461v2","url_pdf":"https://arxiv.org/pdf/2110.09461v2.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":"in-a-nutshell-the-human-asked-for-this-latent-1","repo_url":"https://github.com/bgleon/latent-goal-architectures","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.09461","atlas_url":"https://app.syntology.ai/?focus=2110.09461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09461"}},"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/bgleon/latent-goal-architectures","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"33382c71ea15c795","entry":"MGrid_evaluation","repo":"bgleon/latent-goal-architectures","repo_kind":"official","path":"agents/neuro_symbolic_agent.py","file_url":"https://github.com/bgleon/latent-goal-architectures/blob/HEAD/agents/neuro_symbolic_agent.py","link_basis":"harvester_set","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":"33382c71ea15c795"}},{"code_sha256_prefix":"0b7115fd495eeaf0","entry":"Mcraft_evaluation","repo":"bgleon/latent-goal-architectures","repo_kind":"official","path":"agents/neuro_symbolic_agent.py","file_url":"https://github.com/bgleon/latent-goal-architectures/blob/HEAD/agents/neuro_symbolic_agent.py","link_basis":"harvester_set","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":"0b7115fd495eeaf0"}},{"code_sha256_prefix":"59df34732c3e3418","entry":"downsample","repo":"bgleon/latent-goal-architectures","repo_kind":"official","path":"gym_minigrid/rendering.py","file_url":"https://github.com/bgleon/latent-goal-architectures/blob/HEAD/gym_minigrid/rendering.py","link_basis":"harvester_set","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":"59df34732c3e3418"}},{"code_sha256_prefix":"bd9c272b32f75522","entry":"fill_coords","repo":"bgleon/latent-goal-architectures","repo_kind":"official","path":"gym_minigrid/rendering.py","file_url":"https://github.com/bgleon/latent-goal-architectures/blob/HEAD/gym_minigrid/rendering.py","link_basis":"harvester_set","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":"bd9c272b32f75522"}},{"code_sha256_prefix":"8990d1cc61cec299","entry":"rotate_fn","repo":"bgleon/latent-goal-architectures","repo_kind":"official","path":"gym_minigrid/rendering.py","file_url":"https://github.com/bgleon/latent-goal-architectures/blob/HEAD/gym_minigrid/rendering.py","link_basis":"harvester_set","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":"8990d1cc61cec299"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}