{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I2HO6GNYYXHKWICMLMNTSFRZ22","short_pith_number":"pith:I2HO6GNY","schema_version":"1.0","canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","source":{"kind":"arxiv","id":"2507.07848","version":2},"attestation_state":"computed","paper":{"title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giovanni Dispoto, Marcello Restelli, Paolo Bonetti","submitted_at":"2025-07-10T15:27:44Z","abstract_excerpt":"Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the ability to tackle complex games such as Atari, Go, and other real-world applications, including financial trading. Nevertheless, a significant challenge emerges from the lack of interpretability, particularly when attempting to comprehend the underlying patterns learned, the relative importance of the state features, and how they are integrated to generate t"},"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":"2507.07848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","cross_cats_sorted":[],"title_canon_sha256":"3f2fc7243f25d285cc5d48b47a40ecd09341851b171d707ec97915d5cbbb1333","abstract_canon_sha256":"dc7e0065590fe1e59dc8b9d3d46180f04741942e6b1eccfdf5c6e3012155c75d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:51.033229Z","signature_b64":"vNEjXGIRYW0lOE6+6+/a0qfV5lZUqfIlLKYB+Lf75E3t/7fU81lc+l4UAnGvHvx5by/2BwbZbiIt53OZkAK8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","last_reissued_at":"2026-07-05T11:44:51.032686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:51.032686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giovanni Dispoto, Marcello Restelli, Paolo Bonetti","submitted_at":"2025-07-10T15:27:44Z","abstract_excerpt":"Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the ability to tackle complex games such as Atari, Go, and other real-world applications, including financial trading. Nevertheless, a significant challenge emerges from the lack of interpretability, particularly when attempting to comprehend the underlying patterns learned, the relative importance of the state features, and how they are integrated to generate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07848","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/2507.07848/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":"2507.07848","created_at":"2026-07-05T11:44:51.032743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07848v2","created_at":"2026-07-05T11:44:51.032743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07848","created_at":"2026-07-05T11:44:51.032743+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2HO6GNYYXHK","created_at":"2026-07-05T11:44:51.032743+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2HO6GNYYXHKWICM","created_at":"2026-07-05T11:44:51.032743+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2HO6GNY","created_at":"2026-07-05T11:44:51.032743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13332","citing_title":"Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22","json":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22.json","graph_json":"https://pith.science/api/pith-number/I2HO6GNYYXHKWICMLMNTSFRZ22/graph.json","events_json":"https://pith.science/api/pith-number/I2HO6GNYYXHKWICMLMNTSFRZ22/events.json","paper":"https://pith.science/paper/I2HO6GNY"},"agent_actions":{"view_html":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22","download_json":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22.json","view_paper":"https://pith.science/paper/I2HO6GNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07848&json=true","fetch_graph":"https://pith.science/api/pith-number/I2HO6GNYYXHKWICMLMNTSFRZ22/graph.json","fetch_events":"https://pith.science/api/pith-number/I2HO6GNYYXHKWICMLMNTSFRZ22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/action/storage_attestation","attest_author":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/action/author_attestation","sign_citation":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/action/citation_signature","submit_replication":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/action/replication_record"}},"created_at":"2026-07-05T11:44:51.032743+00:00","updated_at":"2026-07-05T11:44:51.032743+00:00"}