{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IE2FBE7LG2L53YYA6JUOHIUYZB","short_pith_number":"pith:IE2FBE7L","canonical_record":{"source":{"id":"1908.08773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T04:19:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"beb69a5370d7ef45ce3059390f6c4c0594903074b5c232863b38e1e303decc51","abstract_canon_sha256":"ebb53a64c97d297c6bca4d4ea0081fda70124eb0b84e4e732ca95573e2163491"},"schema_version":"1.0"},"canonical_sha256":"41345093eb3697dde300f268e3a298c871a523e8432846e31f906237c5e35137","source":{"kind":"arxiv","id":"1908.08773","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08773","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08773v2","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08773","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"IE2FBE7LG2L5","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"IE2FBE7LG2L53YYA","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"IE2FBE7L","created_at":"2026-07-04T23:59:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IE2FBE7LG2L53YYA6JUOHIUYZB","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T04:19:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"beb69a5370d7ef45ce3059390f6c4c0594903074b5c232863b38e1e303decc51","abstract_canon_sha256":"ebb53a64c97d297c6bca4d4ea0081fda70124eb0b84e4e732ca95573e2163491"},"schema_version":"1.0"},"canonical_sha256":"41345093eb3697dde300f268e3a298c871a523e8432846e31f906237c5e35137","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:35.090273Z","signature_b64":"Tx0HBqtOmkrKySPdxBDvfAU8hNbzKO1CqSamEshpgKuud1tEG6kszE3RsmNOKzZzv2K4pU7H/QEHLqeCKnWhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41345093eb3697dde300f268e3a298c871a523e8432846e31f906237c5e35137","last_reissued_at":"2026-07-04T23:59:35.089938Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:35.089938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08773","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89dxTl+quzHY1Zn1suy9z18qVw9puvwsylGkwcx3kRF5vbA1UiBppqe6DqQu5Cfbv2jwzic6qgFdvcFaoPN5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:35:06.676369Z"},"content_sha256":"1cebe0132c5b177872c27c2fbc74c6ce4e12d63755de0b7bdfca80600129c95b","schema_version":"1.0","event_id":"sha256:1cebe0132c5b177872c27c2fbc74c6ce4e12d63755de0b7bdfca80600129c95b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IE2FBE7LG2L53YYA6JUOHIUYZB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Opponent Aware Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Gomez-Ullate Oteiza, David Rios Insua, Roi Naveiro, Victor Gallego","submitted_at":"2019-08-22T04:19:12Z","abstract_excerpt":"We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL). TMDPs allow suporting a decision maker against potential opponents in a RL context. We also propose a level-k thinking scheme resulting in a novel learning approach to deal with TMDPs. After introducing our framework and deriving theoretical results, relevant empirical evidence is given via extensive experiments, showing the benefits of accounting for adversaries in RL while the agent learns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08773","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08773/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3X4Vg6pHtqZkwYF9X5QBCyQPZ7/j77zHvlOEuJMmAjcK9o/BvVYqoroam51ioO0q4h3VUN50V9usw+cD5WoICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:35:06.677177Z"},"content_sha256":"f65e85a77c4bc571939848d570d4b658c3756a0941732ef872fa81d4e260aeb3","schema_version":"1.0","event_id":"sha256:f65e85a77c4bc571939848d570d4b658c3756a0941732ef872fa81d4e260aeb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/bundle.json","state_url":"https://pith.science/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/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":"2026-08-16T10:35:06Z","links":{"resolver":"https://pith.science/pith/IE2FBE7LG2L53YYA6JUOHIUYZB","bundle":"https://pith.science/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/bundle.json","state":"https://pith.science/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IE2FBE7LG2L53YYA6JUOHIUYZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IE2FBE7LG2L53YYA6JUOHIUYZB","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":"ebb53a64c97d297c6bca4d4ea0081fda70124eb0b84e4e732ca95573e2163491","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T04:19:12Z","title_canon_sha256":"beb69a5370d7ef45ce3059390f6c4c0594903074b5c232863b38e1e303decc51"},"schema_version":"1.0","source":{"id":"1908.08773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08773","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08773v2","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08773","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"IE2FBE7LG2L5","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"IE2FBE7LG2L53YYA","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"IE2FBE7L","created_at":"2026-07-04T23:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:f65e85a77c4bc571939848d570d4b658c3756a0941732ef872fa81d4e260aeb3","target":"graph","created_at":"2026-07-04T23:59:35Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL). TMDPs allow suporting a decision maker against potential opponents in a RL context. We also propose a level-k thinking scheme resulting in a novel learning approach to deal with TMDPs. After introducing our framework and deriving theoretical results, relevant empirical evidence is given via extensive experiments, showing the benefits of accounting for adversaries in RL while the agent learns","authors_text":"David Gomez-Ullate Oteiza, David Rios Insua, Roi Naveiro, Victor Gallego","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T04:19:12Z","title":"Opponent Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08773","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":"sha256:1cebe0132c5b177872c27c2fbc74c6ce4e12d63755de0b7bdfca80600129c95b","target":"record","created_at":"2026-07-04T23:59:35Z","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":"ebb53a64c97d297c6bca4d4ea0081fda70124eb0b84e4e732ca95573e2163491","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T04:19:12Z","title_canon_sha256":"beb69a5370d7ef45ce3059390f6c4c0594903074b5c232863b38e1e303decc51"},"schema_version":"1.0","source":{"id":"1908.08773","kind":"arxiv","version":2}},"canonical_sha256":"41345093eb3697dde300f268e3a298c871a523e8432846e31f906237c5e35137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41345093eb3697dde300f268e3a298c871a523e8432846e31f906237c5e35137","first_computed_at":"2026-07-04T23:59:35.089938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:35.089938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tx0HBqtOmkrKySPdxBDvfAU8hNbzKO1CqSamEshpgKuud1tEG6kszE3RsmNOKzZzv2K4pU7H/QEHLqeCKnWhCA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:35.090273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cebe0132c5b177872c27c2fbc74c6ce4e12d63755de0b7bdfca80600129c95b","sha256:f65e85a77c4bc571939848d570d4b658c3756a0941732ef872fa81d4e260aeb3"],"state_sha256":"6f2abfe792d872648c34e72578fe82c4b63890b0f3139bcd497f8aa73a92f3be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkbu5+r1sAUDmLygSxyOrFF+OT2J3hzR5XsaLN1SFfzTPCyDQEQR4qNfp8ObFlg21nqPTeu0w1D6hLxMOpBSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:35:06.682808Z","bundle_sha256":"3fcf4fe3250e2278356312e2ba4695917c577d8454c75aca9e6df8ff5a97d1d4"}}