{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VQNYBKMMAQD7VCKSZELDQGPXZF","short_pith_number":"pith:VQNYBKMM","schema_version":"1.0","canonical_sha256":"ac1b80a98c0407fa8952c9163819f7c97af9e762e253e2381824e39bceb61a75","source":{"kind":"arxiv","id":"1706.01077","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1706.01077","created_at":"2026-05-18T00:43:04.590625+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01077v1","created_at":"2026-05-18T00:43:04.590625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01077","created_at":"2026-05-18T00:43:04.590625+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQNYBKMMAQD7","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQNYBKMMAQD7VCKS","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQNYBKMM","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF","json":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF.json","graph_json":"https://pith.science/api/pith-number/VQNYBKMMAQD7VCKSZELDQGPXZF/graph.json","events_json":"https://pith.science/api/pith-number/VQNYBKMMAQD7VCKSZELDQGPXZF/events.json","paper":"https://pith.science/paper/VQNYBKMM"},"agent_actions":{"view_html":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF","download_json":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF.json","view_paper":"https://pith.science/paper/VQNYBKMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01077&json=true","fetch_graph":"https://pith.science/api/pith-number/VQNYBKMMAQD7VCKSZELDQGPXZF/graph.json","fetch_events":"https://pith.science/api/pith-number/VQNYBKMMAQD7VCKSZELDQGPXZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/action/storage_attestation","attest_author":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/action/author_attestation","sign_citation":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/action/citation_signature","submit_replication":"https://pith.science/pith/VQNYBKMMAQD7VCKSZELDQGPXZF/action/replication_record"}},"created_at":"2026-05-18T00:43:04.590625+00:00","updated_at":"2026-05-18T00:43:04.590625+00:00"}