{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:X2HLGVJPPJPE5VLHFCLT4RU7D4","short_pith_number":"pith:X2HLGVJP","schema_version":"1.0","canonical_sha256":"be8eb3552f7a5e4ed56728973e469f1f18d56452062b2ccf091acb0142862c38","source":{"kind":"arxiv","id":"2006.15085","version":1},"attestation_state":"computed","paper":{"title":"What can I do here? A Theory of Affordances in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Abel, Doina Precup, Gheorghe Comanici, Khimya Khetarpal, Zafarali Ahmed","submitted_at":"2020-06-26T16:34:53Z","abstract_excerpt":"Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term \"affordances\" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reduci"},"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":"2006.15085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T16:34:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5ee4eec79ffbf3818d315c30604f64c93648194e94ceeb025b0c24828bb09e9e","abstract_canon_sha256":"46b2518a1a9d34dd4c988b9f95b7207419351c6c2d9e73db76bc8587e6eeaa8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:49.490439Z","signature_b64":"HA71LEvH8zr00Izk3Z2c/rl/OLeFred50YOmGIx07nLc0T2B1MFC2XIrXS7aMsiKv/jnMhXGnkZk3XpGlufkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be8eb3552f7a5e4ed56728973e469f1f18d56452062b2ccf091acb0142862c38","last_reissued_at":"2026-07-05T01:13:49.490060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:49.490060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What can I do here? A Theory of Affordances in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Abel, Doina Precup, Gheorghe Comanici, Khimya Khetarpal, Zafarali Ahmed","submitted_at":"2020-06-26T16:34:53Z","abstract_excerpt":"Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term \"affordances\" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reduci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15085","kind":"arxiv","version":1},"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/2006.15085/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":"2006.15085","created_at":"2026-07-05T01:13:49.490121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.15085v1","created_at":"2026-07-05T01:13:49.490121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15085","created_at":"2026-07-05T01:13:49.490121+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2HLGVJPPJPE","created_at":"2026-07-05T01:13:49.490121+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2HLGVJPPJPE5VLH","created_at":"2026-07-05T01:13:49.490121+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2HLGVJP","created_at":"2026-07-05T01:13:49.490121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4","json":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4.json","graph_json":"https://pith.science/api/pith-number/X2HLGVJPPJPE5VLHFCLT4RU7D4/graph.json","events_json":"https://pith.science/api/pith-number/X2HLGVJPPJPE5VLHFCLT4RU7D4/events.json","paper":"https://pith.science/paper/X2HLGVJP"},"agent_actions":{"view_html":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4","download_json":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4.json","view_paper":"https://pith.science/paper/X2HLGVJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.15085&json=true","fetch_graph":"https://pith.science/api/pith-number/X2HLGVJPPJPE5VLHFCLT4RU7D4/graph.json","fetch_events":"https://pith.science/api/pith-number/X2HLGVJPPJPE5VLHFCLT4RU7D4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4/action/storage_attestation","attest_author":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4/action/author_attestation","sign_citation":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4/action/citation_signature","submit_replication":"https://pith.science/pith/X2HLGVJPPJPE5VLHFCLT4RU7D4/action/replication_record"}},"created_at":"2026-07-05T01:13:49.490121+00:00","updated_at":"2026-07-05T01:13:49.490121+00:00"}