{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NRF4RUB37A572QCWIO2RPZJPCE","short_pith_number":"pith:NRF4RUB3","schema_version":"1.0","canonical_sha256":"6c4bc8d03bf83bfd405643b517e52f1121e427b5f010312a1cc5ee1486141381","source":{"kind":"arxiv","id":"2104.01506","version":2},"attestation_state":"computed","paper":{"title":"Influencing Reinforcement Learning through Natural Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Habarakadage Perera, Md Sultan Al Nahian, Tasmia Tasrin","submitted_at":"2021-04-04T00:23:39Z","abstract_excerpt":"Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known Interactive reinforcement learning technique. Usually policy shaping employs a human feedback policy to help an agent to learn "},"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":"2104.01506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-04-04T00:23:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16c960e811a2b9bf5b4071778143bf8011f354a22100f2e1a6461af9d486f8fc","abstract_canon_sha256":"2b5f509bb0b0dc0d65dac63ec3d9c92363af8961f59118d784ef64d5ccbf2859"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:05.274508Z","signature_b64":"KkSrccr6rtyXGdT8Ur/RsFLosjc2DTT0iXfJJV++qHAoSlOgA+AwSAv/KCzjnUVCvKcCarWtrNTJQQT3M3fvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4bc8d03bf83bfd405643b517e52f1121e427b5f010312a1cc5ee1486141381","last_reissued_at":"2026-07-05T02:31:05.274086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:05.274086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Influencing Reinforcement Learning through Natural Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Habarakadage Perera, Md Sultan Al Nahian, Tasmia Tasrin","submitted_at":"2021-04-04T00:23:39Z","abstract_excerpt":"Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known Interactive reinforcement learning technique. Usually policy shaping employs a human feedback policy to help an agent to learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01506","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/2104.01506/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":"2104.01506","created_at":"2026-07-05T02:31:05.274144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01506v2","created_at":"2026-07-05T02:31:05.274144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01506","created_at":"2026-07-05T02:31:05.274144+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRF4RUB37A57","created_at":"2026-07-05T02:31:05.274144+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRF4RUB37A572QCW","created_at":"2026-07-05T02:31:05.274144+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRF4RUB3","created_at":"2026-07-05T02:31:05.274144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14457","citing_title":"Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE","json":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE.json","graph_json":"https://pith.science/api/pith-number/NRF4RUB37A572QCWIO2RPZJPCE/graph.json","events_json":"https://pith.science/api/pith-number/NRF4RUB37A572QCWIO2RPZJPCE/events.json","paper":"https://pith.science/paper/NRF4RUB3"},"agent_actions":{"view_html":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE","download_json":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE.json","view_paper":"https://pith.science/paper/NRF4RUB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01506&json=true","fetch_graph":"https://pith.science/api/pith-number/NRF4RUB37A572QCWIO2RPZJPCE/graph.json","fetch_events":"https://pith.science/api/pith-number/NRF4RUB37A572QCWIO2RPZJPCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE/action/storage_attestation","attest_author":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE/action/author_attestation","sign_citation":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE/action/citation_signature","submit_replication":"https://pith.science/pith/NRF4RUB37A572QCWIO2RPZJPCE/action/replication_record"}},"created_at":"2026-07-05T02:31:05.274144+00:00","updated_at":"2026-07-05T02:31:05.274144+00:00"}