{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VQNYBKMMAQD7VCKSZELDQGPXZF","short_pith_number":"pith:VQNYBKMM","canonical_record":{"source":{"id":"1706.01077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-04T14:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"d9667cdbdf5e6dfec929156a14aa19f2e8450294e304855883ee04a9ba72a49b","abstract_canon_sha256":"1bca7916184e47f4c5a5f129927f70b2b66ffb26a4ad18a0c7a82324b9d649c7"},"schema_version":"1.0"},"canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","source":{"kind":"arxiv","id":"1706.01077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01077","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01077v1","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01077","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"VQNYBKMMAQD7","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VQNYBKMMAQD7VCKS","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VQNYBKMM","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VQNYBKMMAQD7VCKSZELDQGPXZF","target":"record","payload":{"canonical_record":{"source":{"id":"1706.01077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-04T14:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"d9667cdbdf5e6dfec929156a14aa19f2e8450294e304855883ee04a9ba72a49b","abstract_canon_sha256":"1bca7916184e47f4c5a5f129927f70b2b66ffb26a4ad18a0c7a82324b9d649c7"},"schema_version":"1.0"},"canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:04.591251Z","signature_b64":"maaz+1AXiJZtUbzncB+CSR10BEaINYKvsGndWinXwZ1UuMZzdW+inpHdddD14xbuav5phOAtoC8IpLMfOBY2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","last_reissued_at":"2026-05-18T00:43:04.590515Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:04.590515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.01077","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":"2026-05-18T00:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYIMsJy5TPBptG1tpVY7aJ3gNi/ehA6fPVtWxlXpiVBNLCGvjWgAFS6VJI7P8BcqZh2pKgWZh9AluUx0sPgBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:20:21.574467Z"},"content_sha256":"5b77dddfad0095e0d1ff8d9c840fb74eec0a6c259b49baed8bd29384c0aa6e0b","schema_version":"1.0","event_id":"sha256:5b77dddfad0095e0d1ff8d9c840fb74eec0a6c259b49baed8bd29384c0aa6e0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VQNYBKMMAQD7VCKSZELDQGPXZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Danil Prokhorov, Michael R. James, Prashant Doshi, Tomoki Nishi","submitted_at":"2017-06-04T14:02:01Z","abstract_excerpt":"In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning (RL) method for continuous state and action spaces that learns with partial knowledge of the system and without active exploration. It solves linearly-solvable Markov decision processes (L-MDPs), which are well suited for continuous state and action spaces, based on an actor-critic architecture. Compared to previous RL methods for L-MDPs and path integral methods which are model based, the actor-critic learning does"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01077","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":"2026-05-18T00:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAMGTqXrwnQ8wcRCcclHQbUWOFY4JLStuhYXmh3uDtrweP2fVbDBZm37Cc2AQvxu5cEZFtA2pS5gKV/jlVZRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:20:21.574823Z"},"content_sha256":"f63525c9d304a96b99fd05aa14f830a97b6ecd632dc53fdc58015a62e5a381c7","schema_version":"1.0","event_id":"sha256:f63525c9d304a96b99fd05aa14f830a97b6ecd632dc53fdc58015a62e5a381c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/bundle.json","state_url":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/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":"2026-06-02T01:20:21Z","links":{"resolver":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF","bundle":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/bundle.json","state":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VQNYBKMMAQD7VCKSZELDQGPXZF","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":"1bca7916184e47f4c5a5f129927f70b2b66ffb26a4ad18a0c7a82324b9d649c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-04T14:02:01Z","title_canon_sha256":"d9667cdbdf5e6dfec929156a14aa19f2e8450294e304855883ee04a9ba72a49b"},"schema_version":"1.0","source":{"id":"1706.01077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01077","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01077v1","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01077","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"VQNYBKMMAQD7","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VQNYBKMMAQD7VCKS","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VQNYBKMM","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:f63525c9d304a96b99fd05aa14f830a97b6ecd632dc53fdc58015a62e5a381c7","target":"graph","created_at":"2026-05-18T00:43:04Z","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":"In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning (RL) method for continuous state and action spaces that learns with partial knowledge of the system and without active exploration. It solves linearly-solvable Markov decision processes (L-MDPs), which are well suited for continuous state and action spaces, based on an actor-critic architecture. Compared to previous RL methods for L-MDPs and path integral methods which are model based, the actor-critic learning does","authors_text":"Danil Prokhorov, Michael R. James, Prashant Doshi, Tomoki Nishi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-04T14:02:01Z","title":"Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01077","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":"sha256:5b77dddfad0095e0d1ff8d9c840fb74eec0a6c259b49baed8bd29384c0aa6e0b","target":"record","created_at":"2026-05-18T00:43:04Z","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":"1bca7916184e47f4c5a5f129927f70b2b66ffb26a4ad18a0c7a82324b9d649c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-04T14:02:01Z","title_canon_sha256":"d9667cdbdf5e6dfec929156a14aa19f2e8450294e304855883ee04a9ba72a49b"},"schema_version":"1.0","source":{"id":"1706.01077","kind":"arxiv","version":1}},"canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","first_computed_at":"2026-05-18T00:43:04.590515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:04.590515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"maaz+1AXiJZtUbzncB+CSR10BEaINYKvsGndWinXwZ1UuMZzdW+inpHdddD14xbuav5phOAtoC8IpLMfOBY2Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:04.591251Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.01077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b77dddfad0095e0d1ff8d9c840fb74eec0a6c259b49baed8bd29384c0aa6e0b","sha256:f63525c9d304a96b99fd05aa14f830a97b6ecd632dc53fdc58015a62e5a381c7"],"state_sha256":"f9b87329a5d10a945d63dc132ddea378fc146f5e75bc29ab4e8d5649e43e7ee9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zf2sY+ltwCtrhouv/RxQ+q5pA0qRceoLaAvX/gHxEh/Gg1FrupaotDRhUH9ukCOlishh6mS43novBsje9bAQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:20:21.576865Z","bundle_sha256":"e9123d1cffe8d63c7d406fb32a72cdac57ee2bdd3bcd4e62e95c99f44d4c0674"}}