{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3WKDFXXKMFRK5PCXPJ35HE3SQD","short_pith_number":"pith:3WKDFXXK","canonical_record":{"source":{"id":"2303.13489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T17:53:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"62dc4b9522bb82b2fc7a8783e61aed83ad9df9f7a40c23bf06ed5c5a1de56421","abstract_canon_sha256":"51e5bd6648a34f1b86a6156fb05560ced5e2c48cbb6051c294a95035d87d56d7"},"schema_version":"1.0"},"canonical_sha256":"dd9432deea6162aebc577a77d3937280ec25733c906f021ed5f19d4dd25734d5","source":{"kind":"arxiv","id":"2303.13489","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13489","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13489v2","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13489","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_12","alias_value":"3WKDFXXKMFRK","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_16","alias_value":"3WKDFXXKMFRK5PCX","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_8","alias_value":"3WKDFXXK","created_at":"2026-07-05T05:55:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3WKDFXXKMFRK5PCXPJ35HE3SQD","target":"record","payload":{"canonical_record":{"source":{"id":"2303.13489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T17:53:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"62dc4b9522bb82b2fc7a8783e61aed83ad9df9f7a40c23bf06ed5c5a1de56421","abstract_canon_sha256":"51e5bd6648a34f1b86a6156fb05560ced5e2c48cbb6051c294a95035d87d56d7"},"schema_version":"1.0"},"canonical_sha256":"dd9432deea6162aebc577a77d3937280ec25733c906f021ed5f19d4dd25734d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:22.939052Z","signature_b64":"Fa1Ax1e97S0VVRPPpj7ZPEGQ3s+CeHUcCIZgCvBPG9v0fOMSZrye4PLYtisVI/2rL5xceeI8YYJ4Ir9PB+MWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd9432deea6162aebc577a77d3937280ec25733c906f021ed5f19d4dd25734d5","last_reissued_at":"2026-07-05T05:55:22.938682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:22.938682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.13489","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:55:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7XsEkl9oTD8GyyLUqGQX0sO1QypTluD/GCHvKK4TTj3MR+F6gN6jU+5vEWWYyrd8YqRaAeGYet6ueP8KLkPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:53:59.822364Z"},"content_sha256":"16417e9ebdff1c801a641d7a35ce208f3052fb6106073ebff6591581569b983e","schema_version":"1.0","event_id":"sha256:16417e9ebdff1c801a641d7a35ce208f3052fb6106073ebff6591581569b983e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3WKDFXXKMFRK5PCXPJ35HE3SQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao Su, Tongzhou Mu","submitted_at":"2023-03-23T17:53:44Z","abstract_excerpt":"Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit from expert knowledge rather than having to discover the best action to take through exploration. In this survey, we discuss the advantages of using demonstrations in sequential decision making, various ways to apply demonstrations in learning-based decision making paradigms (for example, reinforcement learning and planning in the learned models), and how to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13489","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/2303.13489/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:55:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixrDNSFe+7y9yT6xOVP/2NkYMj8/gQ0cMw452eGOcmQzMzxcunh9V0wPRRxAfqcR04W9tnJPvSLCCORVxT45Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:53:59.823226Z"},"content_sha256":"691f24bc1bcac3ed92e007e0ba121a4e5aed71bd15eb859f46f4f3a7ea8d4ee0","schema_version":"1.0","event_id":"sha256:691f24bc1bcac3ed92e007e0ba121a4e5aed71bd15eb859f46f4f3a7ea8d4ee0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/bundle.json","state_url":"https://pith.science/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/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":"2026-07-07T05:53:59Z","links":{"resolver":"https://pith.science/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD","bundle":"https://pith.science/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/bundle.json","state":"https://pith.science/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WKDFXXKMFRK5PCXPJ35HE3SQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3WKDFXXKMFRK5PCXPJ35HE3SQD","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":"51e5bd6648a34f1b86a6156fb05560ced5e2c48cbb6051c294a95035d87d56d7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T17:53:44Z","title_canon_sha256":"62dc4b9522bb82b2fc7a8783e61aed83ad9df9f7a40c23bf06ed5c5a1de56421"},"schema_version":"1.0","source":{"id":"2303.13489","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13489","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13489v2","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13489","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_12","alias_value":"3WKDFXXKMFRK","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_16","alias_value":"3WKDFXXKMFRK5PCX","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_8","alias_value":"3WKDFXXK","created_at":"2026-07-05T05:55:22Z"}],"graph_snapshots":[{"event_id":"sha256:691f24bc1bcac3ed92e007e0ba121a4e5aed71bd15eb859f46f4f3a7ea8d4ee0","target":"graph","created_at":"2026-07-05T05:55:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.13489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit from expert knowledge rather than having to discover the best action to take through exploration. In this survey, we discuss the advantages of using demonstrations in sequential decision making, various ways to apply demonstrations in learning-based decision making paradigms (for example, reinforcement learning and planning in the learned models), and how to ","authors_text":"Hao Su, Tongzhou Mu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T17:53:44Z","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13489","kind":"arxiv","version":2},"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":"sha256:16417e9ebdff1c801a641d7a35ce208f3052fb6106073ebff6591581569b983e","target":"record","created_at":"2026-07-05T05:55:22Z","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":"51e5bd6648a34f1b86a6156fb05560ced5e2c48cbb6051c294a95035d87d56d7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T17:53:44Z","title_canon_sha256":"62dc4b9522bb82b2fc7a8783e61aed83ad9df9f7a40c23bf06ed5c5a1de56421"},"schema_version":"1.0","source":{"id":"2303.13489","kind":"arxiv","version":2}},"canonical_sha256":"dd9432deea6162aebc577a77d3937280ec25733c906f021ed5f19d4dd25734d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd9432deea6162aebc577a77d3937280ec25733c906f021ed5f19d4dd25734d5","first_computed_at":"2026-07-05T05:55:22.938682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:22.938682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fa1Ax1e97S0VVRPPpj7ZPEGQ3s+CeHUcCIZgCvBPG9v0fOMSZrye4PLYtisVI/2rL5xceeI8YYJ4Ir9PB+MWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:22.939052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13489","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16417e9ebdff1c801a641d7a35ce208f3052fb6106073ebff6591581569b983e","sha256:691f24bc1bcac3ed92e007e0ba121a4e5aed71bd15eb859f46f4f3a7ea8d4ee0"],"state_sha256":"daab0eb031f4846f267ed960592919ec958c79207e0bfcda03630a148eb83753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zyGs7CpzYmTTaS9I4ZQIhkvLHNw7Q6Ct8oXsgZ1JP6S3A/GAzKkI2yZknXFbB6fa1dVEno8dVvwilcjQ6gUDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:53:59.826454Z","bundle_sha256":"85b04435840241388c9eb6593b14ca5a9c83c3957fe3713fcd82ab4229e46c67"}}