{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/procedural-generalization-by-planning-with-1","title":"Procedural Generalization by Planning with Self-Supervised World Models","arxiv_id":"2111.01587","date":"2021-11-02","proceeding":"ICLR 2022 4","authors":["Ankesh Anand","Jacob Walker","Yazhe Li","Eszter Vértes","Julian Schrittwieser","Sherjil Ozair","Théophane Weber","Jessica B. Hamrick"],"abstract":"One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents is not well understood because existing work has focused on model-free agents when benchmarking generalization. Here, we explicitly measure the generalization ability of model-based agents in comparison to their model-free counterparts. We focus our analysis on MuZero (Schrittwieser et al., 2020), a powerful model-based agent, and evaluate its performance on both procedural and task generalization. We identify three factors of procedural generalization -- planning, self-supervised representation learning, and procedural data diversity -- and show that by combining these techniques, we achieve state-of-the art generalization performance and data efficiency on Procgen (Cobbe et al., 2019). However, we find that these factors do not always provide the same benefits for the task generalization benchmarks in Meta-World (Yu et al., 2019), indicating that transfer remains a challenge and may require different approaches than procedural generalization. Overall, we suggest that building generalizable agents requires moving beyond the single-task, model-free paradigm and towards self-supervised model-based agents that are trained in rich, procedural, multi-task environments.","url_abs":"https://arxiv.org/abs/2111.01587v1","url_pdf":"https://arxiv.org/pdf/2111.01587v1.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":[],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"monte-carlo-tree-search","method_name":"Monte-Carlo Tree Search"},{"method_slug":"muzero","method_name":"MuZero"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/meta-learning-on-ml10","task":"Meta-Learning","dataset":"ML10","model":"MZ+Recon","rank_in_archive_order":5,"of":6,"metrics":{"Meta-test success rate (zero-shot)":"25","Meta-train success rate":"97.8%"},"uses_additional_data":false},{"leaderboard":"/sota/meta-learning-on-ml10","task":"Meta-Learning","dataset":"ML10","model":"MZ","rank_in_archive_order":6,"of":6,"metrics":{"Meta-test success rate (zero-shot)":"26.5","Meta-train success rate":"97.6%"},"uses_additional_data":false},{"leaderboard":"/sota/meta-learning-on-ml45","task":"Meta-Learning","dataset":"ML45","model":"MZ+Recon","rank_in_archive_order":1,"of":2,"metrics":{"Meta-test success rate (zero-shot)":"18.5","Meta-train success rate":"74.9"},"uses_additional_data":false},{"leaderboard":"/sota/meta-learning-on-ml45","task":"Meta-Learning","dataset":"ML45","model":"MZ","rank_in_archive_order":2,"of":2,"metrics":{"Meta-test success rate (zero-shot)":"17.7","Meta-train success rate":"77.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.01587","atlas_url":"https://app.syntology.ai/?focus=2111.01587","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.01587"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.01587\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.01587"},"call":"get_concepts_for_paper(arxiv_id=\"2111.01587\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7fd918ceec8a0d3a1f4a83bea3e2e712c497e4c8323be05a728d6cda054100fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}