{"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/generalization-to-new-actions-in-1","title":"Generalization to New Actions in Reinforcement Learning","arxiv_id":"2011.01928","date":"2020-11-03","proceeding":"ICML 2020 1","authors":["Ayush Jain","Andrew Szot","Joseph J. Lim"],"abstract":"A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires expensive retraining when given a new action set. To make learning agents more adaptable, we introduce the problem of zero-shot generalization to new actions. We propose a two-stage framework where the agent first infers action representations from action information acquired separately from the task. A policy flexible to varying action sets is then trained with generalization objectives. We benchmark generalization on sequential tasks, such as selecting from an unseen tool-set to solve physical reasoning puzzles and stacking towers with novel 3D shapes. Videos and code are available at https://sites.google.com/view/action-generalization","url_abs":"https://arxiv.org/abs/2011.01928v1","url_pdf":"https://arxiv.org/pdf/2011.01928v1.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":"generalization-to-new-actions-in-1","repo_url":"https://github.com/clvrai/new-actions-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"generalization-to-new-actions-in-1","repo_url":"https://github.com/clvrai/create","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.01928","atlas_url":"https://app.syntology.ai/?focus=2011.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01928"}},"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/clvrai/new-actions-rl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clvrai/create","reach":null}],"summary":{"ran":14,"ran_draft_wrong":2,"ran_honours":2,"unverified":3},"by_repo_kind":{"official":{"samples":21,"ran":18,"repositories":2}},"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":20,"samples":[{"code_sha256_prefix":"2549d67825e3fb58","entry":"Beta","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2549d67825e3fb58"}},{"code_sha256_prefix":"dd4a9f0d253bfe90","entry":"CNNBase_NEW","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd4a9f0d253bfe90"}},{"code_sha256_prefix":"2e0973cb87fadfb6","entry":"Categorical","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e0973cb87fadfb6"}},{"code_sha256_prefix":"93b65a059eba1be7","entry":"ConditionedAuxDist","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93b65a059eba1be7"}},{"code_sha256_prefix":"c2bdefbcdfe3a875","entry":"ConditionedAuxWrapper","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2bdefbcdfe3a875"}},{"code_sha256_prefix":"2062968c588d48da","entry":"Conv2d3x3","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2062968c588d48da"}},{"code_sha256_prefix":"c3e91ef2c04afa28","entry":"DiagGaussian","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3e91ef2c04afa28"}},{"code_sha256_prefix":"91666da04aaa6ba4","entry":"DiagGaussianVariance","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91666da04aaa6ba4"}},{"code_sha256_prefix":"c72079105e05daaa","entry":"DistWrapper","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c72079105e05daaa"}},{"code_sha256_prefix":"0c518a49b21b3a37","entry":"MLPBase","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c518a49b21b3a37"}},{"code_sha256_prefix":"5ad49de4aa356408","entry":"MixedDist","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ad49de4aa356408"}},{"code_sha256_prefix":"4f7b9c26206107af","entry":"NNBase","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f7b9c26206107af"}},{"code_sha256_prefix":"5113f693aa39c008","entry":"OrderInvariantCategorical","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5113f693aa39c008"}},{"code_sha256_prefix":"08477ea65294ed85","entry":"RndCategorical","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"08477ea65294ed85"}},{"code_sha256_prefix":"c790bb0df379811f","entry":"add_mag_stats","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c790bb0df379811f"}},{"code_sha256_prefix":"0e7b0c51b3d70736","entry":"extract_aval","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e7b0c51b3d70736"}},{"code_sha256_prefix":"72d99a8e5cd83dc8","entry":"init_extract_aval","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72d99a8e5cd83dc8"}},{"code_sha256_prefix":"be293701f9986ccd","entry":"split_action_set","repo":"clvrai/create","repo_kind":"official","path":"create_game/create_action_set.py","file_url":"https://github.com/clvrai/create/blob/HEAD/create_game/create_action_set.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be293701f9986ccd"}},{"code_sha256_prefix":"7da11c67fbcd655c","entry":"ActorCritic","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7da11c67fbcd655c"}},{"code_sha256_prefix":"e8e8cf08b831157a","entry":"BasePolicy","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8e8cf08b831157a"}},{"code_sha256_prefix":"e09457d2f83e11bc","entry":"MainMethod","repo":"clvrai/new-actions-rl","repo_kind":"official","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e09457d2f83e11bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}