{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DUCNE4AMJH2QPECADCQQBUC262","short_pith_number":"pith:DUCNE4AM","canonical_record":{"source":{"id":"1709.10089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:48Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO"],"title_canon_sha256":"b82cb3dcfe88db3f6f906ad539222ab5a63bc94acd5fba6f2c79c62969841369","abstract_canon_sha256":"4aed394a5018bd7a864ec59793c704619bc48062ece3e1734db28e1ccfb29cb3"},"schema_version":"1.0"},"canonical_sha256":"1d04d2700c49f507904018a100d05af6bb91df136dee96e2ed18811f367c9255","source":{"kind":"arxiv","id":"1709.10089","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.10089","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"1709.10089v2","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10089","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"DUCNE4AMJH2Q","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DUCNE4AMJH2QPECA","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DUCNE4AM","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DUCNE4AMJH2QPECADCQQBUC262","target":"record","payload":{"canonical_record":{"source":{"id":"1709.10089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:48Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO"],"title_canon_sha256":"b82cb3dcfe88db3f6f906ad539222ab5a63bc94acd5fba6f2c79c62969841369","abstract_canon_sha256":"4aed394a5018bd7a864ec59793c704619bc48062ece3e1734db28e1ccfb29cb3"},"schema_version":"1.0"},"canonical_sha256":"1d04d2700c49f507904018a100d05af6bb91df136dee96e2ed18811f367c9255","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.464934Z","signature_b64":"OYSfssTGQfbmr9mYkps5aAk4o1AiKXaoMpyKobuGQJWOiB3imT2z1t9wbd/YNJoLncgPQOWMlM0bMbPtL3gaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d04d2700c49f507904018a100d05af6bb91df136dee96e2ed18811f367c9255","last_reissued_at":"2026-05-18T00:22:39.464291Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.464291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.10089","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":"2026-05-18T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PmNKfVpiyZJh6xzpTpYCQbwkailyz2KAyTc6v1pourO102WZIGvMucUTP7Kb/dxePHD0C4LX4v1kg6L7cK66CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:11:18.024611Z"},"content_sha256":"fc075fbb8e12fc949bb81ddc765dbbe4fe0e64ca46c79eed2f892252586e816a","schema_version":"1.0","event_id":"sha256:fc075fbb8e12fc949bb81ddc765dbbe4fe0e64ca46c79eed2f892252586e816a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DUCNE4AMJH2QPECADCQQBUC262","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ashvin Nair, Bob McGrew, Marcin Andrychowicz, Pieter Abbeel, Wojciech Zaremba","submitted_at":"2017-09-28T17:51:48Z","abstract_excerpt":"Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10089","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":""},"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":"2026-05-18T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GfhFjA3LY8W/YvNvb2vw05miGOe1pXkwvhKeNBA/QnKSVRRxpMuRIk9CUt3By4gbE5Qk4gSejbZSDmLpVLd8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:11:18.024955Z"},"content_sha256":"5e2d98643c311c4e8f62c89e31643e598343af58b895fcac7075d43013658891","schema_version":"1.0","event_id":"sha256:5e2d98643c311c4e8f62c89e31643e598343af58b895fcac7075d43013658891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUCNE4AMJH2QPECADCQQBUC262/bundle.json","state_url":"https://pith.science/pith/DUCNE4AMJH2QPECADCQQBUC262/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUCNE4AMJH2QPECADCQQBUC262/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":"2026-06-01T04:11:18Z","links":{"resolver":"https://pith.science/pith/DUCNE4AMJH2QPECADCQQBUC262","bundle":"https://pith.science/pith/DUCNE4AMJH2QPECADCQQBUC262/bundle.json","state":"https://pith.science/pith/DUCNE4AMJH2QPECADCQQBUC262/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUCNE4AMJH2QPECADCQQBUC262/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DUCNE4AMJH2QPECADCQQBUC262","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":"4aed394a5018bd7a864ec59793c704619bc48062ece3e1734db28e1ccfb29cb3","cross_cats_sorted":["cs.AI","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:48Z","title_canon_sha256":"b82cb3dcfe88db3f6f906ad539222ab5a63bc94acd5fba6f2c79c62969841369"},"schema_version":"1.0","source":{"id":"1709.10089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.10089","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"1709.10089v2","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10089","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"DUCNE4AMJH2Q","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DUCNE4AMJH2QPECA","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DUCNE4AM","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:5e2d98643c311c4e8f62c89e31643e598343af58b895fcac7075d43013658891","target":"graph","created_at":"2026-05-18T00:22:39Z","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 in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous con","authors_text":"Ashvin Nair, Bob McGrew, Marcin Andrychowicz, Pieter Abbeel, Wojciech Zaremba","cross_cats":["cs.AI","cs.NE","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:48Z","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10089","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:fc075fbb8e12fc949bb81ddc765dbbe4fe0e64ca46c79eed2f892252586e816a","target":"record","created_at":"2026-05-18T00:22:39Z","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":"4aed394a5018bd7a864ec59793c704619bc48062ece3e1734db28e1ccfb29cb3","cross_cats_sorted":["cs.AI","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:48Z","title_canon_sha256":"b82cb3dcfe88db3f6f906ad539222ab5a63bc94acd5fba6f2c79c62969841369"},"schema_version":"1.0","source":{"id":"1709.10089","kind":"arxiv","version":2}},"canonical_sha256":"1d04d2700c49f507904018a100d05af6bb91df136dee96e2ed18811f367c9255","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d04d2700c49f507904018a100d05af6bb91df136dee96e2ed18811f367c9255","first_computed_at":"2026-05-18T00:22:39.464291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:39.464291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OYSfssTGQfbmr9mYkps5aAk4o1AiKXaoMpyKobuGQJWOiB3imT2z1t9wbd/YNJoLncgPQOWMlM0bMbPtL3gaBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:39.464934Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.10089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc075fbb8e12fc949bb81ddc765dbbe4fe0e64ca46c79eed2f892252586e816a","sha256:5e2d98643c311c4e8f62c89e31643e598343af58b895fcac7075d43013658891"],"state_sha256":"6edd302b0620be084142c4e01864d5b8f8c3cdc7d74ec894bfdada2c2847899b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrR1587QViO0xDk3RdgZyRk0QCtoAISdBmPjJpnL+iZ9/bOrS22/hwlYtiT0kJKZbWO6PahbpTlHFfZM3QZWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:11:18.026872Z","bundle_sha256":"d512eb67b8ffd4963a6534749fc07c8b5c682d38ca13384d95b076ce3b83aeea"}}