{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZK7CV33ZRSLON3OTEWTRLFI5IO","short_pith_number":"pith:ZK7CV33Z","canonical_record":{"source":{"id":"1906.03574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T06:00:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e0bee8264091e91a2a1500b9e180813908b23e60cc6b791ed4de005dd98d5f00","abstract_canon_sha256":"6ad03281f011bb39515bb342da70504909af9819403ed80ec69bd6f068bbd16f"},"schema_version":"1.0"},"canonical_sha256":"cabe2aef798c96e6edd325a715951d439eb099c419ed17e70e69cfc12771678d","source":{"kind":"arxiv","id":"1906.03574","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03574","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03574v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03574","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZK7CV33ZRSLO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZK7CV33ZRSLON3OT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZK7CV33Z","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZK7CV33ZRSLON3OTEWTRLFI5IO","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T06:00:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e0bee8264091e91a2a1500b9e180813908b23e60cc6b791ed4de005dd98d5f00","abstract_canon_sha256":"6ad03281f011bb39515bb342da70504909af9819403ed80ec69bd6f068bbd16f"},"schema_version":"1.0"},"canonical_sha256":"cabe2aef798c96e6edd325a715951d439eb099c419ed17e70e69cfc12771678d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:48.073853Z","signature_b64":"Rfo8pLMz+fDRO9VPJe0u7Zf9VLAHs38r6Dycp8psuoYrSlibOu5qoXTpJ+Nh354WNHr0yzEY70FE5SJOW8NNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabe2aef798c96e6edd325a715951d439eb099c419ed17e70e69cfc12771678d","last_reissued_at":"2026-05-17T23:43:48.073289Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:48.073289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03574","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+/BtRKCGZQRcA79GW3KISaJTIZfh2UL69RJPc0yJKdIO23gPClBBRn/17bmE2ZxxRFJjJuQ9V8Dw74j6PIf4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:02:13.185242Z"},"content_sha256":"4ba8ef497c60726f0d405e93f47e5b3b4955583e049f8e7a49574a4fe10c8c97","schema_version":"1.0","event_id":"sha256:4ba8ef497c60726f0d405e93f47e5b3b4955583e049f8e7a49574a4fe10c8c97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZK7CV33ZRSLON3OTEWTRLFI5IO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer Learning by Modeling a Distribution over Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Disha Shrivastava, Eeshan Gunesh Dhekane, Riashat Islam","submitted_at":"2019-06-09T06:00:50Z","abstract_excerpt":"Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning setup to propose a transfer strategy. Recent works have shown to induce diversity in the learned policies by maximizing the entropy of a distribution of policies (Bachman et al., 2018; Garnelo et al., 2018) and thus, we postulate that our proposed approach leads to faster exploration resulting in improved transfer learning. We support our hypothesis by demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03574","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bod0DRj6KysQQUx8xz1rVJn6zgHcRRrwsbGNJGCbTjlpMTRLpZ+6ztsjPm4fEL7uxUICUWk2K+EqV01d0vaNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:02:13.185622Z"},"content_sha256":"f731c8efdd1698de908c254f0d07ce4aadb56fc7ac9b4a281c627ae148669a6e","schema_version":"1.0","event_id":"sha256:f731c8efdd1698de908c254f0d07ce4aadb56fc7ac9b4a281c627ae148669a6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/bundle.json","state_url":"https://pith.science/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T03:02:13Z","links":{"resolver":"https://pith.science/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO","bundle":"https://pith.science/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/bundle.json","state":"https://pith.science/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK7CV33ZRSLON3OTEWTRLFI5IO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZK7CV33ZRSLON3OTEWTRLFI5IO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6ad03281f011bb39515bb342da70504909af9819403ed80ec69bd6f068bbd16f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T06:00:50Z","title_canon_sha256":"e0bee8264091e91a2a1500b9e180813908b23e60cc6b791ed4de005dd98d5f00"},"schema_version":"1.0","source":{"id":"1906.03574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03574","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03574v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03574","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZK7CV33ZRSLO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZK7CV33ZRSLON3OT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZK7CV33Z","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f731c8efdd1698de908c254f0d07ce4aadb56fc7ac9b4a281c627ae148669a6e","target":"graph","created_at":"2026-05-17T23:43:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning setup to propose a transfer strategy. Recent works have shown to induce diversity in the learned policies by maximizing the entropy of a distribution of policies (Bachman et al., 2018; Garnelo et al., 2018) and thus, we postulate that our proposed approach leads to faster exploration resulting in improved transfer learning. We support our hypothesis by demonstr","authors_text":"Disha Shrivastava, Eeshan Gunesh Dhekane, Riashat Islam","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T06:00:50Z","title":"Transfer Learning by Modeling a Distribution over Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03574","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ba8ef497c60726f0d405e93f47e5b3b4955583e049f8e7a49574a4fe10c8c97","target":"record","created_at":"2026-05-17T23:43:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6ad03281f011bb39515bb342da70504909af9819403ed80ec69bd6f068bbd16f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T06:00:50Z","title_canon_sha256":"e0bee8264091e91a2a1500b9e180813908b23e60cc6b791ed4de005dd98d5f00"},"schema_version":"1.0","source":{"id":"1906.03574","kind":"arxiv","version":1}},"canonical_sha256":"cabe2aef798c96e6edd325a715951d439eb099c419ed17e70e69cfc12771678d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabe2aef798c96e6edd325a715951d439eb099c419ed17e70e69cfc12771678d","first_computed_at":"2026-05-17T23:43:48.073289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:48.073289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rfo8pLMz+fDRO9VPJe0u7Zf9VLAHs38r6Dycp8psuoYrSlibOu5qoXTpJ+Nh354WNHr0yzEY70FE5SJOW8NNDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:48.073853Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ba8ef497c60726f0d405e93f47e5b3b4955583e049f8e7a49574a4fe10c8c97","sha256:f731c8efdd1698de908c254f0d07ce4aadb56fc7ac9b4a281c627ae148669a6e"],"state_sha256":"4f4c75c40fcb120bed950d0c0938371dcf46183d5a3e50ccb478c3ee3387f531"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xRpM1Yp+jFda3OrF8IYIIJoIIrnabR8pBSPkkv3u3/8Ig/OExvzb9XxB1YWpHHXgKhC13o78QLOZOYlPFyljAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T03:02:13.189006Z","bundle_sha256":"3c9049e7a378879230dc6662c678d33c682840f9b89eff97723b3a0f89fc1840"}}