{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KGE4AUYHYTCJ4LQ52K4ODC67E7","short_pith_number":"pith:KGE4AUYH","canonical_record":{"source":{"id":"1705.01399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-03T13:13:51Z","cross_cats_sorted":[],"title_canon_sha256":"8eda9bae89b6925bf93c96298e2e52b7fdee2ef17e5a73b7e05facd7355cb9fe","abstract_canon_sha256":"2a082ad6fdaa5252f63609773e14bad5137c4fd587907ef6504fe2f4fb134cb0"},"schema_version":"1.0"},"canonical_sha256":"5189c05307c4c49e2e1dd2b8e18bdf27d4405b15fe6efc04bcbcfc82dac34db6","source":{"kind":"arxiv","id":"1705.01399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01399","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01399v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01399","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"KGE4AUYHYTCJ","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KGE4AUYHYTCJ4LQ5","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KGE4AUYH","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KGE4AUYHYTCJ4LQ52K4ODC67E7","target":"record","payload":{"canonical_record":{"source":{"id":"1705.01399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-03T13:13:51Z","cross_cats_sorted":[],"title_canon_sha256":"8eda9bae89b6925bf93c96298e2e52b7fdee2ef17e5a73b7e05facd7355cb9fe","abstract_canon_sha256":"2a082ad6fdaa5252f63609773e14bad5137c4fd587907ef6504fe2f4fb134cb0"},"schema_version":"1.0"},"canonical_sha256":"5189c05307c4c49e2e1dd2b8e18bdf27d4405b15fe6efc04bcbcfc82dac34db6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:05.256487Z","signature_b64":"xE1KCTSPW6j7r8QN3ExeFi6/La0ZJgiY6Jr2LKGpHMkuGp5mIQsfMf9VAYWIigVXxhy5tMqA6nZIORQJhCV2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5189c05307c4c49e2e1dd2b8e18bdf27d4405b15fe6efc04bcbcfc82dac34db6","last_reissued_at":"2026-05-18T00:45:05.256074Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:05.256074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.01399","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQZ8zOfii8GSKRzl4o6f1WtP2uq4ZexsLwm2s/RBrhHnESIIMNSEaEVY0DsE6n5NPDqyYp01eZZzKt2mcMxADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:10:28.550143Z"},"content_sha256":"6bd451864db64e34c7ea975cb8b18efe335377821b719808d4bb9fa59df2a66e","schema_version":"1.0","event_id":"sha256:6bd451864db64e34c7ea975cb8b18efe335377821b719808d4bb9fa59df2a66e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KGE4AUYHYTCJ4LQ52K4ODC67E7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Answer Set Programming for Non-Stationary Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","submitted_at":"2017-05-03T13:13:51Z","abstract_excerpt":"Non-stationary domains, where unforeseen changes happen, present a challenge for agents to find an optimal policy for a sequential decision making problem. This work investigates a solution to this problem that combines Markov Decision Processes (MDP) and Reinforcement Learning (RL) with Answer Set Programming (ASP) in a method we call ASP(RL). In this method, Answer Set Programming is used to find the possible trajectories of an MDP, from where Reinforcement Learning is applied to learn the optimal policy of the problem. Results show that ASP(RL) is capable of efficiently finding the optimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01399","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mz1tH372UIyCfXg0632VJaLdb/s/Ht4an3vHE+1GLbl57PfCzT0FchU8YFuiJ86jSZ+zpKIAGukaTiNFjCiDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:10:28.550510Z"},"content_sha256":"7cb5805ae5d17be30852d06611544d0e3d5e3ea247b5de163beb05d84cf060df","schema_version":"1.0","event_id":"sha256:7cb5805ae5d17be30852d06611544d0e3d5e3ea247b5de163beb05d84cf060df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/bundle.json","state_url":"https://pith.science/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/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":"2026-06-06T12:10:28Z","links":{"resolver":"https://pith.science/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7","bundle":"https://pith.science/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/bundle.json","state":"https://pith.science/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KGE4AUYHYTCJ4LQ52K4ODC67E7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KGE4AUYHYTCJ4LQ52K4ODC67E7","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":"2a082ad6fdaa5252f63609773e14bad5137c4fd587907ef6504fe2f4fb134cb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-03T13:13:51Z","title_canon_sha256":"8eda9bae89b6925bf93c96298e2e52b7fdee2ef17e5a73b7e05facd7355cb9fe"},"schema_version":"1.0","source":{"id":"1705.01399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01399","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01399v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01399","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"KGE4AUYHYTCJ","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KGE4AUYHYTCJ4LQ5","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KGE4AUYH","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:7cb5805ae5d17be30852d06611544d0e3d5e3ea247b5de163beb05d84cf060df","target":"graph","created_at":"2026-05-18T00:45:05Z","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":"Non-stationary domains, where unforeseen changes happen, present a challenge for agents to find an optimal policy for a sequential decision making problem. This work investigates a solution to this problem that combines Markov Decision Processes (MDP) and Reinforcement Learning (RL) with Answer Set Programming (ASP) in a method we call ASP(RL). In this method, Answer Set Programming is used to find the possible trajectories of an MDP, from where Reinforcement Learning is applied to learn the optimal policy of the problem. Results show that ASP(RL) is capable of efficiently finding the optimal ","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-03T13:13:51Z","title":"Answer Set Programming for Non-Stationary Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01399","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":"sha256:6bd451864db64e34c7ea975cb8b18efe335377821b719808d4bb9fa59df2a66e","target":"record","created_at":"2026-05-18T00:45:05Z","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":"2a082ad6fdaa5252f63609773e14bad5137c4fd587907ef6504fe2f4fb134cb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-03T13:13:51Z","title_canon_sha256":"8eda9bae89b6925bf93c96298e2e52b7fdee2ef17e5a73b7e05facd7355cb9fe"},"schema_version":"1.0","source":{"id":"1705.01399","kind":"arxiv","version":1}},"canonical_sha256":"5189c05307c4c49e2e1dd2b8e18bdf27d4405b15fe6efc04bcbcfc82dac34db6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5189c05307c4c49e2e1dd2b8e18bdf27d4405b15fe6efc04bcbcfc82dac34db6","first_computed_at":"2026-05-18T00:45:05.256074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:05.256074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xE1KCTSPW6j7r8QN3ExeFi6/La0ZJgiY6Jr2LKGpHMkuGp5mIQsfMf9VAYWIigVXxhy5tMqA6nZIORQJhCV2Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:05.256487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.01399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bd451864db64e34c7ea975cb8b18efe335377821b719808d4bb9fa59df2a66e","sha256:7cb5805ae5d17be30852d06611544d0e3d5e3ea247b5de163beb05d84cf060df"],"state_sha256":"98829a17a8e509150dc992d981bd55871b0143b4683f9b17bf267f22501f448f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhEyv/YIUughL/DUVv2H7ReF26kkYZZluXgsaXXFquPgluHb8JWcvyZQXlWVQLMu8o/FUa6OLB9l8SptUQphDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T12:10:28.553114Z","bundle_sha256":"6c07109aa57f234ad8be4a2dfa8b6b5747cca162a51a15bdb155d150f60734b6"}}