{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CCHQBM7XCPMXEGK45I5ROH7QFC","short_pith_number":"pith:CCHQBM7X","schema_version":"1.0","canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","source":{"kind":"arxiv","id":"2605.30928","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Shah Ali, Fawad Javed Fateh, M. Shaheer Luqman, Murad Popattia, M. Zeeshan Zia, Quoc-Huy Tran, Usman Nizamani","submitted_at":"2026-05-29T07:18:20Z","abstract_excerpt":"Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limiting interpretability and reliability. In this work, we introduce a novel human-like RL framework that predicts action sequences closely aligned with human behaviors while maximizing rewards. Specifically, we encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ) consisting of two successive levels of vector quantizati"},"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":"2605.30928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"7db9c1b5841d9fc4088c0555aa45acfb5e051deba24eb479b9e2828bdd160ef6","abstract_canon_sha256":"5587a1e71a7422233360ac1d6f7fcd59843ffd32d058e311a31e76e964614c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:26.398085Z","signature_b64":"uOfZQRvzu/orUADeyKxJKGJXWvz9sP4imHuRqNUWSx2XatkLQOkvgBgdCrzhWocuOy1HYqSNV1xYfMxmapRbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","last_reissued_at":"2026-06-01T01:03:26.397144Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:26.397144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Shah Ali, Fawad Javed Fateh, M. Shaheer Luqman, Murad Popattia, M. Zeeshan Zia, Quoc-Huy Tran, Usman Nizamani","submitted_at":"2026-05-29T07:18:20Z","abstract_excerpt":"Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limiting interpretability and reliability. In this work, we introduce a novel human-like RL framework that predicts action sequences closely aligned with human behaviors while maximizing rewards. Specifically, we encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ) consisting of two successive levels of vector quantizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30928","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/2605.30928/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":"2605.30928","created_at":"2026-06-01T01:03:26.397248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30928v1","created_at":"2026-06-01T01:03:26.397248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30928","created_at":"2026-06-01T01:03:26.397248+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCHQBM7XCPMX","created_at":"2026-06-01T01:03:26.397248+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCHQBM7XCPMXEGK4","created_at":"2026-06-01T01:03:26.397248+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCHQBM7X","created_at":"2026-06-01T01:03:26.397248+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/CCHQBM7XCPMXEGK45I5ROH7QFC","json":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC.json","graph_json":"https://pith.science/api/pith-number/CCHQBM7XCPMXEGK45I5ROH7QFC/graph.json","events_json":"https://pith.science/api/pith-number/CCHQBM7XCPMXEGK45I5ROH7QFC/events.json","paper":"https://pith.science/paper/CCHQBM7X"},"agent_actions":{"view_html":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC","download_json":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC.json","view_paper":"https://pith.science/paper/CCHQBM7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30928&json=true","fetch_graph":"https://pith.science/api/pith-number/CCHQBM7XCPMXEGK45I5ROH7QFC/graph.json","fetch_events":"https://pith.science/api/pith-number/CCHQBM7XCPMXEGK45I5ROH7QFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/action/storage_attestation","attest_author":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/action/author_attestation","sign_citation":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/action/citation_signature","submit_replication":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/action/replication_record"}},"created_at":"2026-06-01T01:03:26.397248+00:00","updated_at":"2026-06-01T01:03:26.397248+00:00"}