{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QZM55HQ3M6WUM2DMP2OWYB5ZN5","short_pith_number":"pith:QZM55HQ3","schema_version":"1.0","canonical_sha256":"8659de9e1b67ad46686c7e9d6c07b96f5aaabb91f2bbea5950fbe56821193eb6","source":{"kind":"arxiv","id":"2104.06600","version":1},"attestation_state":"computed","paper":{"title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bo He, Guangliang Li, Jie Huang, Keisuke Nakamura, Qixin Sha, Randy Gomez, Rongshun Juan","submitted_at":"2021-04-14T02:58:51Z","abstract_excerpt":"Deep reinforcement learning (DRL) has achieved great successes in many simulated tasks. The sample inefficiency problem makes applying traditional DRL methods to real-world robots a great challenge. Generative Adversarial Imitation Learning (GAIL) -- a general model-free imitation learning method, allows robots to directly learn policies from expert trajectories in large environments. However, GAIL shares the limitation of other imitation learning methods that they can seldom surpass the performance of demonstrations. In this paper, to address the limit of GAIL, we propose GAN-Based Interactiv"},"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":"2104.06600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T02:58:51Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e62cddd392a3acdca31ed43ddef383096723b70618bd09e3b28863d33ed0cfbc","abstract_canon_sha256":"ba42705023e2005bcdf3e0f85413b6ded9f5a5d2c15dd4f9326722be23654825"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:07.406896Z","signature_b64":"/Y/89mYo1r7sxl32zr5JziAVu0JfQp5Kgw2akMbB2iAVgwtYQ7x4nfzup6rCM+2/pRdmJNWVgH8gEqg4XRrzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8659de9e1b67ad46686c7e9d6c07b96f5aaabb91f2bbea5950fbe56821193eb6","last_reissued_at":"2026-07-05T02:32:07.406436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:07.406436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bo He, Guangliang Li, Jie Huang, Keisuke Nakamura, Qixin Sha, Randy Gomez, Rongshun Juan","submitted_at":"2021-04-14T02:58:51Z","abstract_excerpt":"Deep reinforcement learning (DRL) has achieved great successes in many simulated tasks. The sample inefficiency problem makes applying traditional DRL methods to real-world robots a great challenge. Generative Adversarial Imitation Learning (GAIL) -- a general model-free imitation learning method, allows robots to directly learn policies from expert trajectories in large environments. However, GAIL shares the limitation of other imitation learning methods that they can seldom surpass the performance of demonstrations. In this paper, to address the limit of GAIL, we propose GAN-Based Interactiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06600","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/2104.06600/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":"2104.06600","created_at":"2026-07-05T02:32:07.406537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06600v1","created_at":"2026-07-05T02:32:07.406537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06600","created_at":"2026-07-05T02:32:07.406537+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZM55HQ3M6WU","created_at":"2026-07-05T02:32:07.406537+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZM55HQ3M6WUM2DM","created_at":"2026-07-05T02:32:07.406537+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZM55HQ3","created_at":"2026-07-05T02:32:07.406537+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/QZM55HQ3M6WUM2DMP2OWYB5ZN5","json":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5.json","graph_json":"https://pith.science/api/pith-number/QZM55HQ3M6WUM2DMP2OWYB5ZN5/graph.json","events_json":"https://pith.science/api/pith-number/QZM55HQ3M6WUM2DMP2OWYB5ZN5/events.json","paper":"https://pith.science/paper/QZM55HQ3"},"agent_actions":{"view_html":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5","download_json":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5.json","view_paper":"https://pith.science/paper/QZM55HQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06600&json=true","fetch_graph":"https://pith.science/api/pith-number/QZM55HQ3M6WUM2DMP2OWYB5ZN5/graph.json","fetch_events":"https://pith.science/api/pith-number/QZM55HQ3M6WUM2DMP2OWYB5ZN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5/action/storage_attestation","attest_author":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5/action/author_attestation","sign_citation":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5/action/citation_signature","submit_replication":"https://pith.science/pith/QZM55HQ3M6WUM2DMP2OWYB5ZN5/action/replication_record"}},"created_at":"2026-07-05T02:32:07.406537+00:00","updated_at":"2026-07-05T02:32:07.406537+00:00"}