{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UY2SFVGCZL2DJSOMICOTECNFHT","short_pith_number":"pith:UY2SFVGC","canonical_record":{"source":{"id":"2005.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T19:18:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7cd7980cc31e8c80c19934b57c0b20f32f101b29f76c6a1fafb078284b2480bd","abstract_canon_sha256":"fae3f2b3d63ae0a8fa5652e11f7f5d00f3adc9dbb102d0899f9cd939becfcef9"},"schema_version":"1.0"},"canonical_sha256":"a63522d4c2caf434c9cc409d3209a53cda7f14411770e3230006b12cd6b1d469","source":{"kind":"arxiv","id":"2005.08068","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08068","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08068v1","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08068","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"UY2SFVGCZL2D","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"UY2SFVGCZL2DJSOM","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"UY2SFVGC","created_at":"2026-07-05T01:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UY2SFVGCZL2DJSOMICOTECNFHT","target":"record","payload":{"canonical_record":{"source":{"id":"2005.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T19:18:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7cd7980cc31e8c80c19934b57c0b20f32f101b29f76c6a1fafb078284b2480bd","abstract_canon_sha256":"fae3f2b3d63ae0a8fa5652e11f7f5d00f3adc9dbb102d0899f9cd939becfcef9"},"schema_version":"1.0"},"canonical_sha256":"a63522d4c2caf434c9cc409d3209a53cda7f14411770e3230006b12cd6b1d469","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:27.708139Z","signature_b64":"of6ohvopxmRKPF2GtCT+PpXZ/kg62/9GqyzDLR+iH6/cs7nMBE2nP0zMbJSaayQKWD4GK0V+2QO2rgB+EdOnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a63522d4c2caf434c9cc409d3209a53cda7f14411770e3230006b12cd6b1d469","last_reissued_at":"2026-07-05T01:03:27.707668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:27.707668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.08068","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":"2026-07-05T01:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFkpMAn+/GAKiz0Ao3B4U3mE5iPwSgaJThzYtVwysTL/86SBa7rtYMLZ8h6XpeOxXIK24imNllD8iV0tPE4+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:00:02.520751Z"},"content_sha256":"4183e19a25124e7151b7ef802b48207267b61caf24a69cc7a9cd50a01c5a1a3e","schema_version":"1.0","event_id":"sha256:4183e19a25124e7151b7ef802b48207267b61caf24a69cc7a9cd50a01c5a1a3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UY2SFVGCZL2DJSOMICOTECNFHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Augmented Actor-Critic: Backpropagating through Paths","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignasi Clavera, Pieter Abbeel, Violet Fu","submitted_at":"2020-05-16T19:18:10Z","abstract_excerpt":"Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the model by exploiting its differentiability. We construct a policy optimization algorithm that uses the pathwise derivative of the learned model and policy across future timesteps. Instabilities of learning across many timesteps are prevented by using a terminal value function, learning the policy in an actor-critic fashion. Furthermore, we present a derivati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08068","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/2005.08068/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":"2026-07-05T01:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MW7e48/90wvz08D0He6CaZTKB3X+3utBIHImIsyyvh32krJuDZvQgQTv6LzPSM8kMxYoZQAo8Afwnn4UlYooAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:00:02.521237Z"},"content_sha256":"753bc0ba3b53b8e619cc4aae0c1366b42386cbf5ff8bfd236843f63791bb55e1","schema_version":"1.0","event_id":"sha256:753bc0ba3b53b8e619cc4aae0c1366b42386cbf5ff8bfd236843f63791bb55e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UY2SFVGCZL2DJSOMICOTECNFHT/bundle.json","state_url":"https://pith.science/pith/UY2SFVGCZL2DJSOMICOTECNFHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UY2SFVGCZL2DJSOMICOTECNFHT/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":"2026-08-11T00:00:02Z","links":{"resolver":"https://pith.science/pith/UY2SFVGCZL2DJSOMICOTECNFHT","bundle":"https://pith.science/pith/UY2SFVGCZL2DJSOMICOTECNFHT/bundle.json","state":"https://pith.science/pith/UY2SFVGCZL2DJSOMICOTECNFHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UY2SFVGCZL2DJSOMICOTECNFHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UY2SFVGCZL2DJSOMICOTECNFHT","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":"fae3f2b3d63ae0a8fa5652e11f7f5d00f3adc9dbb102d0899f9cd939becfcef9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T19:18:10Z","title_canon_sha256":"7cd7980cc31e8c80c19934b57c0b20f32f101b29f76c6a1fafb078284b2480bd"},"schema_version":"1.0","source":{"id":"2005.08068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08068","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08068v1","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08068","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"UY2SFVGCZL2D","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"UY2SFVGCZL2DJSOM","created_at":"2026-07-05T01:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"UY2SFVGC","created_at":"2026-07-05T01:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:753bc0ba3b53b8e619cc4aae0c1366b42386cbf5ff8bfd236843f63791bb55e1","target":"graph","created_at":"2026-07-05T01:03:27Z","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/2005.08068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the model by exploiting its differentiability. We construct a policy optimization algorithm that uses the pathwise derivative of the learned model and policy across future timesteps. Instabilities of learning across many timesteps are prevented by using a terminal value function, learning the policy in an actor-critic fashion. Furthermore, we present a derivati","authors_text":"Ignasi Clavera, Pieter Abbeel, Violet Fu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T19:18:10Z","title":"Model-Augmented Actor-Critic: Backpropagating through Paths"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08068","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":"sha256:4183e19a25124e7151b7ef802b48207267b61caf24a69cc7a9cd50a01c5a1a3e","target":"record","created_at":"2026-07-05T01:03:27Z","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":"fae3f2b3d63ae0a8fa5652e11f7f5d00f3adc9dbb102d0899f9cd939becfcef9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-16T19:18:10Z","title_canon_sha256":"7cd7980cc31e8c80c19934b57c0b20f32f101b29f76c6a1fafb078284b2480bd"},"schema_version":"1.0","source":{"id":"2005.08068","kind":"arxiv","version":1}},"canonical_sha256":"a63522d4c2caf434c9cc409d3209a53cda7f14411770e3230006b12cd6b1d469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a63522d4c2caf434c9cc409d3209a53cda7f14411770e3230006b12cd6b1d469","first_computed_at":"2026-07-05T01:03:27.707668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:27.707668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"of6ohvopxmRKPF2GtCT+PpXZ/kg62/9GqyzDLR+iH6/cs7nMBE2nP0zMbJSaayQKWD4GK0V+2QO2rgB+EdOnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:27.708139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4183e19a25124e7151b7ef802b48207267b61caf24a69cc7a9cd50a01c5a1a3e","sha256:753bc0ba3b53b8e619cc4aae0c1366b42386cbf5ff8bfd236843f63791bb55e1"],"state_sha256":"24c37b42b979bfc218f1dfb798920913bf71285c79162bb78e9ec5386efc6e06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLm4u1m6fRjL+UiRzfVT1ZvnfcC1JJYHEMoeuaNTM2EBCU7j2HTWr+uixFCq1O210f40RISQEbhtxfcm7iYkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:00:02.525520Z","bundle_sha256":"70545aeb040f84532a974fe62a918215f38553b5b525bb4619dfacdf619736d9"}}