{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RAAQVVY6HMPMPRUX22SNFEPPH3","short_pith_number":"pith:RAAQVVY6","schema_version":"1.0","canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","source":{"kind":"arxiv","id":"2411.19418","version":2},"attestation_state":"computed","paper":{"title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Harshit Sikchi, Peter Stone, Siddhant Agarwal","submitted_at":"2024-11-29T00:09:39Z","abstract_excerpt":"Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as \"zero-shot learning\", this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present Proto Successor Measure: the basis set for all possible behaviors of a Reinforcement Learning Agent in a dynamical system. We prove that any poss"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.19418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af67b8b9f1e16f054509e66007c2b55b84954e4062f0184ec413c45474171d4c","abstract_canon_sha256":"e90b2f7d5df78da63055ed46d1f774e379ebfa11f681825b040e1b6e4cdebf51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:28.568284Z","signature_b64":"SXtKTEPDbf4tShRBFNig6zOkbXo+rtsERs62wyUCiq0+SScT/iVZtOVOFx/n5rsgTXpAYaDRVUxiOymwQeZICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","last_reissued_at":"2026-07-05T10:28:28.567465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:28.567465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Harshit Sikchi, Peter Stone, Siddhant Agarwal","submitted_at":"2024-11-29T00:09:39Z","abstract_excerpt":"Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as \"zero-shot learning\", this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present Proto Successor Measure: the basis set for all possible behaviors of a Reinforcement Learning Agent in a dynamical system. We prove that any poss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19418","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.19418/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.19418","created_at":"2026-07-05T10:28:28.567547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19418v2","created_at":"2026-07-05T10:28:28.567547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19418","created_at":"2026-07-05T10:28:28.567547+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAAQVVY6HMPM","created_at":"2026-07-05T10:28:28.567547+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAAQVVY6HMPMPRUX","created_at":"2026-07-05T10:28:28.567547+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAAQVVY6","created_at":"2026-07-05T10:28:28.567547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21271","citing_title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11525","citing_title":"Learning Object Manipulation from Scratch via Contrastive Interaction","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13207","citing_title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3","json":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3.json","graph_json":"https://pith.science/api/pith-number/RAAQVVY6HMPMPRUX22SNFEPPH3/graph.json","events_json":"https://pith.science/api/pith-number/RAAQVVY6HMPMPRUX22SNFEPPH3/events.json","paper":"https://pith.science/paper/RAAQVVY6"},"agent_actions":{"view_html":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3","download_json":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3.json","view_paper":"https://pith.science/paper/RAAQVVY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19418&json=true","fetch_graph":"https://pith.science/api/pith-number/RAAQVVY6HMPMPRUX22SNFEPPH3/graph.json","fetch_events":"https://pith.science/api/pith-number/RAAQVVY6HMPMPRUX22SNFEPPH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/action/storage_attestation","attest_author":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/action/author_attestation","sign_citation":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/action/citation_signature","submit_replication":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/action/replication_record"}},"created_at":"2026-07-05T10:28:28.567547+00:00","updated_at":"2026-07-05T10:28:28.567547+00:00"}