{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BSYWAEZXQMJFLBHUV2U6M4X52E","short_pith_number":"pith:BSYWAEZX","schema_version":"1.0","canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","source":{"kind":"arxiv","id":"1711.01503","version":1},"attestation_state":"computed","paper":{"title":"Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Animesh Garg, Daniel Crankshaw, Joseph E. Gonzalez, Ken Goldberg, Richard Liaw, Sanjay Krishnan","submitted_at":"2017-11-04T22:37:25Z","abstract_excerpt":"Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a \"meta-policy\" from previously learned policies. This paper reports results from experiments using Deep Reinforcement Learning on a continuous-state, discrete-action autonomous driving simulator. We explore how Deep Neural Networks can represent meta-policies that switch among a set of previously learned policies, specifically in settings where the dynamics of a new scenario are composed of a mixture of previously learned dynamics and where the state observation is possibly"},"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":"1711.01503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-04T22:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"5284f19d59b2c09abb315761ba4ff0963aa67df656e9398b95391c9e59752d44","abstract_canon_sha256":"50829c22d1b1a2831755ea8b99b9e75941d280e6f8598e0b12fa71ce8df2c556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:17.630774Z","signature_b64":"gwZpQmsYjTdidMGXeA3Q1ShHiCU5XKXEziSmKr0J1CiIJVvAuASkS4/DtAG/yWbc7gvDvrC+VlBE52GWsCrpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","last_reissued_at":"2026-05-18T00:31:17.630076Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:17.630076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Animesh Garg, Daniel Crankshaw, Joseph E. Gonzalez, Ken Goldberg, Richard Liaw, Sanjay Krishnan","submitted_at":"2017-11-04T22:37:25Z","abstract_excerpt":"Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a \"meta-policy\" from previously learned policies. This paper reports results from experiments using Deep Reinforcement Learning on a continuous-state, discrete-action autonomous driving simulator. We explore how Deep Neural Networks can represent meta-policies that switch among a set of previously learned policies, specifically in settings where the dynamics of a new scenario are composed of a mixture of previously learned dynamics and where the state observation is possibly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01503","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":"1711.01503","created_at":"2026-05-18T00:31:17.630187+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01503v1","created_at":"2026-05-18T00:31:17.630187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01503","created_at":"2026-05-18T00:31:17.630187+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSYWAEZXQMJF","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSYWAEZXQMJFLBHU","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSYWAEZX","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13207","citing_title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E","json":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E.json","graph_json":"https://pith.science/api/pith-number/BSYWAEZXQMJFLBHUV2U6M4X52E/graph.json","events_json":"https://pith.science/api/pith-number/BSYWAEZXQMJFLBHUV2U6M4X52E/events.json","paper":"https://pith.science/paper/BSYWAEZX"},"agent_actions":{"view_html":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E","download_json":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E.json","view_paper":"https://pith.science/paper/BSYWAEZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01503&json=true","fetch_graph":"https://pith.science/api/pith-number/BSYWAEZXQMJFLBHUV2U6M4X52E/graph.json","fetch_events":"https://pith.science/api/pith-number/BSYWAEZXQMJFLBHUV2U6M4X52E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/action/storage_attestation","attest_author":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/action/author_attestation","sign_citation":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/action/citation_signature","submit_replication":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/action/replication_record"}},"created_at":"2026-05-18T00:31:17.630187+00:00","updated_at":"2026-05-18T00:31:17.630187+00:00"}