{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZI6MSBA5JLDLYFKTEBNM2ZBHWI","short_pith_number":"pith:ZI6MSBA5","canonical_record":{"source":{"id":"1802.00332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-01T15:13:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c8daa7407a6f8bbbf808760169f2cf370ec95a49b41440a8f969bacf84703c5","abstract_canon_sha256":"9f29d2039b3db7737cdfa194040a37784920632f63463bda36e7f705c3af3e10"},"schema_version":"1.0"},"canonical_sha256":"ca3cc9041d4ac6bc1553205acd6427b20dcdea5805842a79b74774460ca60892","source":{"kind":"arxiv","id":"1802.00332","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00332","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00332v1","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00332","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZI6MSBA5JLDL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZI6MSBA5JLDLYFKT","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZI6MSBA5","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZI6MSBA5JLDLYFKTEBNM2ZBHWI","target":"record","payload":{"canonical_record":{"source":{"id":"1802.00332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-01T15:13:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c8daa7407a6f8bbbf808760169f2cf370ec95a49b41440a8f969bacf84703c5","abstract_canon_sha256":"9f29d2039b3db7737cdfa194040a37784920632f63463bda36e7f705c3af3e10"},"schema_version":"1.0"},"canonical_sha256":"ca3cc9041d4ac6bc1553205acd6427b20dcdea5805842a79b74774460ca60892","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:36.216452Z","signature_b64":"x1fZhsptov4O8EBobfz5ipRaVQwKHXyyj46pnYE/tZRmaXXA9JwhETWbrxYqvEFMjpfQWQRfAxi+UV9cK0IqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3cc9041d4ac6bc1553205acd6427b20dcdea5805842a79b74774460ca60892","last_reissued_at":"2026-05-18T00:24:36.216086Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:36.216086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.00332","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":"2026-05-18T00:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/53d+PZos0zkL3uyu5VcKVkU00rPQIO2Z5JyavtJFzlfiwM6//8mh1D1Ulta0gS20yMDa8wkjwdnBCoBNkXoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:55:17.414794Z"},"content_sha256":"dd0255e24fd383fb3770c4059618b9392ece69e5b38f03a485cc4004ca4c070f","schema_version":"1.0","event_id":"sha256:dd0255e24fd383fb3770c4059618b9392ece69e5b38f03a485cc4004ca4c070f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZI6MSBA5JLDLYFKTEBNM2ZBHWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chang Huang, Jingchu Liu, Lisen Mu, Pengfei Hou, Yinan Yu","submitted_at":"2018-02-01T15:13:10Z","abstract_excerpt":"Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years. In this paper, we propose several practical components that can speed up deep reinforcement learning algorithms towards tactical decision making tasks: 1) non-uniform action skipping as a more stable alternative to action-repetition frame skipping, 2) a counter-based penalty for lanes on which ego vehicle has less right-of-road, and 3) heuristic inference-time action masking for apparently undesirable actions. We evaluate the proposed components in a realistic dri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00332","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":"2026-05-18T00:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVh0ooJopMFecB5k7EBuauC78f1ief0z6WyPpJiJQ7u3Zv/IO6sAf31ilI6BzWTxMBosswvwOGg9+wSyq9MEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:55:17.415448Z"},"content_sha256":"39732d985dbb11d1f1e693dd78061d01454b42545bf82fb93bb723bb309a7873","schema_version":"1.0","event_id":"sha256:39732d985dbb11d1f1e693dd78061d01454b42545bf82fb93bb723bb309a7873"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/bundle.json","state_url":"https://pith.science/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/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":"2026-05-26T17:55:17Z","links":{"resolver":"https://pith.science/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI","bundle":"https://pith.science/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/bundle.json","state":"https://pith.science/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZI6MSBA5JLDLYFKTEBNM2ZBHWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZI6MSBA5JLDLYFKTEBNM2ZBHWI","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":"9f29d2039b3db7737cdfa194040a37784920632f63463bda36e7f705c3af3e10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-01T15:13:10Z","title_canon_sha256":"1c8daa7407a6f8bbbf808760169f2cf370ec95a49b41440a8f969bacf84703c5"},"schema_version":"1.0","source":{"id":"1802.00332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00332","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00332v1","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00332","created_at":"2026-05-18T00:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZI6MSBA5JLDL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZI6MSBA5JLDLYFKT","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZI6MSBA5","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:39732d985dbb11d1f1e693dd78061d01454b42545bf82fb93bb723bb309a7873","target":"graph","created_at":"2026-05-18T00:24:36Z","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":"Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years. In this paper, we propose several practical components that can speed up deep reinforcement learning algorithms towards tactical decision making tasks: 1) non-uniform action skipping as a more stable alternative to action-repetition frame skipping, 2) a counter-based penalty for lanes on which ego vehicle has less right-of-road, and 3) heuristic inference-time action masking for apparently undesirable actions. We evaluate the proposed components in a realistic dri","authors_text":"Chang Huang, Jingchu Liu, Lisen Mu, Pengfei Hou, Yinan Yu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-01T15:13:10Z","title":"Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00332","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:dd0255e24fd383fb3770c4059618b9392ece69e5b38f03a485cc4004ca4c070f","target":"record","created_at":"2026-05-18T00:24:36Z","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":"9f29d2039b3db7737cdfa194040a37784920632f63463bda36e7f705c3af3e10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-01T15:13:10Z","title_canon_sha256":"1c8daa7407a6f8bbbf808760169f2cf370ec95a49b41440a8f969bacf84703c5"},"schema_version":"1.0","source":{"id":"1802.00332","kind":"arxiv","version":1}},"canonical_sha256":"ca3cc9041d4ac6bc1553205acd6427b20dcdea5805842a79b74774460ca60892","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca3cc9041d4ac6bc1553205acd6427b20dcdea5805842a79b74774460ca60892","first_computed_at":"2026-05-18T00:24:36.216086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:36.216086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1fZhsptov4O8EBobfz5ipRaVQwKHXyyj46pnYE/tZRmaXXA9JwhETWbrxYqvEFMjpfQWQRfAxi+UV9cK0IqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:36.216452Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd0255e24fd383fb3770c4059618b9392ece69e5b38f03a485cc4004ca4c070f","sha256:39732d985dbb11d1f1e693dd78061d01454b42545bf82fb93bb723bb309a7873"],"state_sha256":"ec6e963718c4a295659e0b2b8e1bf533d9cdbb6862a3e96472748c37a6a33e44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KGsjPuWLikqAW6/vHrhqmxCS+w7s6HMPd8760RYf6eFcCR2IeogW1NUZXPiCoyCAa0feur6t2MqtefeEwCrJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:55:17.419005Z","bundle_sha256":"9d2d0160a04c122783c850819d3140908ad0b9bfe362f506092c1422ebe49e78"}}