{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BSYWAEZXQMJFLBHUV2U6M4X52E","short_pith_number":"pith:BSYWAEZX","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"},"canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","source":{"kind":"arxiv","id":"1711.01503","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BSYWAEZXQMJFLBHUV2U6M4X52E","target":"record","payload":{"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"},"canonical_sha256":"0cb160133783125584f4aea9e672fdd130744b7d3116e4f503dba57e6a582273","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"},"source_kind":"arxiv","source_id":"1711.01503","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":"2026-05-18T00:31:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Psj6VwtYXBA6f5Tc0/Uk8TGp58AJ0DL96CCu4FUS69ujRs6KJ35cdkmGhaVZcTJWkJxv80Tl2olQMAdVZTCrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:04:07.263277Z"},"content_sha256":"875255588c9133b267d8c35f163be33f0770261c5b15292910d37b949643a778","schema_version":"1.0","event_id":"sha256:875255588c9133b267d8c35f163be33f0770261c5b15292910d37b949643a778"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BSYWAEZXQMJFLBHUV2U6M4X52E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RyMglJ548TovkLfkQPWsVspvMYpO4/4n3WgB6MgNAgx9b8dPlHvwv7E81ukuU9YfxfOoJzlgYrh6NF8XnGMZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:04:07.263912Z"},"content_sha256":"717ee3fb39b51781a734fd0121d3e8b2c8faf9299c6d7ff16e9c354adc510ba9","schema_version":"1.0","event_id":"sha256:717ee3fb39b51781a734fd0121d3e8b2c8faf9299c6d7ff16e9c354adc510ba9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/bundle.json","state_url":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/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":"2026-05-27T15:04:07Z","links":{"resolver":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E","bundle":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/bundle.json","state":"https://pith.science/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSYWAEZXQMJFLBHUV2U6M4X52E/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QO8/zRJIdfN5o01csXX74OoXTruaeEcX2dqMlTlGeMJqTLvVv+BzX4oiA+J12eFm7YRftuM36/VLBgMO8D+kBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:04:07.267066Z","bundle_sha256":"f7ed6e04941c113eb943c2be0e08379ad1f1ef2b51d9a4f72cd4aab2f55e4a07"}}