{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:CAGCRA6HDVGQLUBTLJN7LXUT4R","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":"189dd6338240c6afd5e2153137a9ec18b92761dd3196620b520fecd536ab2277","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-11T20:43:30Z","title_canon_sha256":"3b82165e03b5cec46fa02f792f27c2d788b4528f3ee721fc1d861ed5ca415fe8"},"schema_version":"1.0","source":{"id":"1612.03471","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03471","created_at":"2026-05-18T00:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03471v2","created_at":"2026-05-18T00:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03471","created_at":"2026-05-18T00:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"CAGCRA6HDVGQ","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CAGCRA6HDVGQLUBT","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CAGCRA6H","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:1530ecfb9a6b381b87c79afab35871d5e3321dacb300a5717493e54974f32684","target":"graph","created_at":"2026-05-18T00:49:41Z","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":"Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the de- sired behavior and constraints of a robot. Usually, these are handcrafted by a expert designer and represent heuristics for relatively simple tasks. Real world applications typically involve more complex tasks with rich temporal and logical structure. In this paper we take advantage of the expressive power of temporal logic (TL) to specify complex rules the robot should follow, and incorporate domain knowledge into learning. We propose Truncated Linear Temporal Logic (TLTL) as specification","authors_text":"Calin Belta, Cristian-Ioan Vasile, Xiao Li","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-11T20:43:30Z","title":"Reinforcement Learning With Temporal Logic Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03471","kind":"arxiv","version":2},"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":"sha256:8a72dfcb87e979a5692f8fdf91da8407c265d604e3a53d393b886c51dff490ce","target":"record","created_at":"2026-05-18T00:49:41Z","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":"189dd6338240c6afd5e2153137a9ec18b92761dd3196620b520fecd536ab2277","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-11T20:43:30Z","title_canon_sha256":"3b82165e03b5cec46fa02f792f27c2d788b4528f3ee721fc1d861ed5ca415fe8"},"schema_version":"1.0","source":{"id":"1612.03471","kind":"arxiv","version":2}},"canonical_sha256":"100c2883c71d4d05d0335a5bf5de93e470a4c61600ca55ff54cafe0d2292110b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"100c2883c71d4d05d0335a5bf5de93e470a4c61600ca55ff54cafe0d2292110b","first_computed_at":"2026-05-18T00:49:41.855334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:41.855334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzywhvRTeLoVingYgtcaNZtwrNcyvj6Ke7HeruM+baTEL38SyuBdJ4t7w9SZC/50J51ovufXSh6TiZz+gGGyBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:41.855865Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.03471","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a72dfcb87e979a5692f8fdf91da8407c265d604e3a53d393b886c51dff490ce","sha256:1530ecfb9a6b381b87c79afab35871d5e3321dacb300a5717493e54974f32684"],"state_sha256":"05a90d17983da63e688d3c1e8bc4e3ef9e062d2cf6581a8adca125194fd3ce2c"}