{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZTOOO4EBSG7LPNM4MIKLXG634K","short_pith_number":"pith:ZTOOO4EB","canonical_record":{"source":{"id":"2408.07712","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T23:08:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b2942bda070fdeb62ea48af16efae4d63629c5785b5b92e90727cb82a087715","abstract_canon_sha256":"e53ed5bd26a4d49f79bfe081906e42ccd66aaf92c0f2e50304feb095c059cb25"},"schema_version":"1.0"},"canonical_sha256":"ccdce7708191beb7b59c6214bb9bdbe2bf58f44559b604fa28820cf9fccaedf3","source":{"kind":"arxiv","id":"2408.07712","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07712","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07712v3","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07712","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZTOOO4EBSG7L","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZTOOO4EBSG7LPNM4","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZTOOO4EB","created_at":"2026-07-05T09:43:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZTOOO4EBSG7LPNM4MIKLXG634K","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07712","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T23:08:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b2942bda070fdeb62ea48af16efae4d63629c5785b5b92e90727cb82a087715","abstract_canon_sha256":"e53ed5bd26a4d49f79bfe081906e42ccd66aaf92c0f2e50304feb095c059cb25"},"schema_version":"1.0"},"canonical_sha256":"ccdce7708191beb7b59c6214bb9bdbe2bf58f44559b604fa28820cf9fccaedf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:32.389109Z","signature_b64":"j8oIQprxTNmZxodtJRbpqTfQauQRHpdQM6Z6exoEtTRXwnCuIX7odhaVpo4Sbru2Y/QOSDHJVRuL2W6sS1dGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccdce7708191beb7b59c6214bb9bdbe2bf58f44559b604fa28820cf9fccaedf3","last_reissued_at":"2026-07-05T09:43:32.388619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:32.388619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07712","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQFTYelW+ruMxxZkdy3ntE0kyPYGkxyQl8eVba9Zl9nONhADoOpx3DUn6sVLs0A/7wKsXj7ubrDYXkARNs6ICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:09:36.153396Z"},"content_sha256":"198e09d0c21ac813ba68b90e95a9a9fa8a191a07b89159f6fd109f69a4afe86c","schema_version":"1.0","event_id":"sha256:198e09d0c21ac813ba68b90e95a9a9fa8a191a07b89159f6fd109f69a4afe86c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZTOOO4EBSG7LPNM4MIKLXG634K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Introduction to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dariush Ebrahimi, Majid Ghasemi","submitted_at":"2024-08-13T23:08:06Z","abstract_excerpt":"Reinforcement Learning (RL), a subfield of Artificial Intelligence (AI), focuses on training agents to make decisions by interacting with their environment to maximize cumulative rewards. This paper provides an overview of RL, covering its core concepts, methodologies, and resources for further learning. It offers a thorough explanation of fundamental components such as states, actions, policies, and reward signals, ensuring readers develop a solid foundational understanding. Additionally, the paper presents a variety of RL algorithms, categorized based on the key factors such as model-free, m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07712","kind":"arxiv","version":3},"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/2408.07712/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":"2026-07-05T09:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cf3FIy3hcwPE9gpLBQjlS4k6pb7HiEBoro2rH+tb4Q++Dl5PpT0PHAFa9owbYHL9RBVlypbbGV5ybxe5el1XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:09:36.154326Z"},"content_sha256":"a09b57826bf7085bb3991eb675fbcf02fe3ecbe02693ff07d92a04fac760d505","schema_version":"1.0","event_id":"sha256:a09b57826bf7085bb3991eb675fbcf02fe3ecbe02693ff07d92a04fac760d505"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/bundle.json","state_url":"https://pith.science/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/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":"2026-08-09T16:09:36Z","links":{"resolver":"https://pith.science/pith/ZTOOO4EBSG7LPNM4MIKLXG634K","bundle":"https://pith.science/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/bundle.json","state":"https://pith.science/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTOOO4EBSG7LPNM4MIKLXG634K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZTOOO4EBSG7LPNM4MIKLXG634K","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":"e53ed5bd26a4d49f79bfe081906e42ccd66aaf92c0f2e50304feb095c059cb25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T23:08:06Z","title_canon_sha256":"8b2942bda070fdeb62ea48af16efae4d63629c5785b5b92e90727cb82a087715"},"schema_version":"1.0","source":{"id":"2408.07712","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07712","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07712v3","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07712","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZTOOO4EBSG7L","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZTOOO4EBSG7LPNM4","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZTOOO4EB","created_at":"2026-07-05T09:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:a09b57826bf7085bb3991eb675fbcf02fe3ecbe02693ff07d92a04fac760d505","target":"graph","created_at":"2026-07-05T09:43:32Z","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/2408.07712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL), a subfield of Artificial Intelligence (AI), focuses on training agents to make decisions by interacting with their environment to maximize cumulative rewards. This paper provides an overview of RL, covering its core concepts, methodologies, and resources for further learning. It offers a thorough explanation of fundamental components such as states, actions, policies, and reward signals, ensuring readers develop a solid foundational understanding. Additionally, the paper presents a variety of RL algorithms, categorized based on the key factors such as model-free, m","authors_text":"Dariush Ebrahimi, Majid Ghasemi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T23:08:06Z","title":"Introduction to Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07712","kind":"arxiv","version":3},"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":"sha256:198e09d0c21ac813ba68b90e95a9a9fa8a191a07b89159f6fd109f69a4afe86c","target":"record","created_at":"2026-07-05T09:43:32Z","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":"e53ed5bd26a4d49f79bfe081906e42ccd66aaf92c0f2e50304feb095c059cb25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T23:08:06Z","title_canon_sha256":"8b2942bda070fdeb62ea48af16efae4d63629c5785b5b92e90727cb82a087715"},"schema_version":"1.0","source":{"id":"2408.07712","kind":"arxiv","version":3}},"canonical_sha256":"ccdce7708191beb7b59c6214bb9bdbe2bf58f44559b604fa28820cf9fccaedf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccdce7708191beb7b59c6214bb9bdbe2bf58f44559b604fa28820cf9fccaedf3","first_computed_at":"2026-07-05T09:43:32.388619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:32.388619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j8oIQprxTNmZxodtJRbpqTfQauQRHpdQM6Z6exoEtTRXwnCuIX7odhaVpo4Sbru2Y/QOSDHJVRuL2W6sS1dGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:32.389109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07712","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:198e09d0c21ac813ba68b90e95a9a9fa8a191a07b89159f6fd109f69a4afe86c","sha256:a09b57826bf7085bb3991eb675fbcf02fe3ecbe02693ff07d92a04fac760d505"],"state_sha256":"8d8dfa110843eb27bb1b983b5c827c8550780e70f845077145bfa0c86c3a5ced"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8piX/4sMBlZT3BrYGxTsVaKuOmNd5Fv9Dcnr8G2mFXn6UnF6TAWS0IaPn2RpXwNoltjnxEr9b2ur5xeBN6lOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:09:36.159511Z","bundle_sha256":"f78c06a1d76c8ab9797e2c87d4df7fe8cbc48daad81d1af2545afda1ede3e424"}}