{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BSYWAEZXQMJFLBHUV2U6M4X52E","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":"50829c22d1b1a2831755ea8b99b9e75941d280e6f8598e0b12fa71ce8df2c556","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-04T22:37:25Z","title_canon_sha256":"5284f19d59b2c09abb315761ba4ff0963aa67df656e9398b95391c9e59752d44"},"schema_version":"1.0","source":{"id":"1711.01503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01503","created_at":"2026-05-18T00:31:17Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01503v1","created_at":"2026-05-18T00:31:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01503","created_at":"2026-05-18T00:31:17Z"},{"alias_kind":"pith_short_12","alias_value":"BSYWAEZXQMJF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BSYWAEZXQMJFLBHU","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BSYWAEZX","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:717ee3fb39b51781a734fd0121d3e8b2c8faf9299c6d7ff16e9c354adc510ba9","target":"graph","created_at":"2026-05-18T00:31:17Z","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":"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","authors_text":"Animesh Garg, Daniel Crankshaw, Joseph E. Gonzalez, Ken Goldberg, Richard Liaw, Sanjay Krishnan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-04T22:37:25Z","title":"Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01503","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":"sha256:875255588c9133b267d8c35f163be33f0770261c5b15292910d37b949643a778","target":"record","created_at":"2026-05-18T00:31:17Z","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":"50829c22d1b1a2831755ea8b99b9e75941d280e6f8598e0b12fa71ce8df2c556","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-04T22:37:25Z","title_canon_sha256":"5284f19d59b2c09abb315761ba4ff0963aa67df656e9398b95391c9e59752d44"},"schema_version":"1.0","source":{"id":"1711.01503","kind":"arxiv","version":1}},"canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","first_computed_at":"2026-05-18T00:31:17.630076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:17.630076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gwZpQmsYjTdidMGXeA3Q1ShHiCU5XKXEziSmKr0J1CiIJVvAuASkS4/DtAG/yWbc7gvDvrC+VlBE52GWsCrpDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:17.630774Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.01503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:875255588c9133b267d8c35f163be33f0770261c5b15292910d37b949643a778","sha256:717ee3fb39b51781a734fd0121d3e8b2c8faf9299c6d7ff16e9c354adc510ba9"],"state_sha256":"2df6ffb6370f299690a3b8cb08881471d287674e7e07885fde3381d4b26c37e4"}