{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FEA7MAY64C7Y56MX5FSBPH3GIZ","short_pith_number":"pith:FEA7MAY6","canonical_record":{"source":{"id":"1905.07727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T11:29:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfa56c1098b24e0c259a6d4b5a5f6c701f3a35bb98ef008cd64e1a728f37db4e","abstract_canon_sha256":"58451b68a3c3e3b5876b8f5634a887a982f776d4308bf43997457e3c4cdc7082"},"schema_version":"1.0"},"canonical_sha256":"2901f6031ee0bf8ef997e964179f664673b81ef59b731a22cdf7cc0b0dd8a366","source":{"kind":"arxiv","id":"1905.07727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07727","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07727v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07727","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"FEA7MAY64C7Y","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FEA7MAY64C7Y56MX","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FEA7MAY6","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FEA7MAY64C7Y56MX5FSBPH3GIZ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T11:29:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfa56c1098b24e0c259a6d4b5a5f6c701f3a35bb98ef008cd64e1a728f37db4e","abstract_canon_sha256":"58451b68a3c3e3b5876b8f5634a887a982f776d4308bf43997457e3c4cdc7082"},"schema_version":"1.0"},"canonical_sha256":"2901f6031ee0bf8ef997e964179f664673b81ef59b731a22cdf7cc0b0dd8a366","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.668161Z","signature_b64":"AKSR2BhN7Jx3GmgPpEtJRA4Wbk8rD3fWjNC50rjKFca5wtwMcA8pvPR1yhSVBlDSxiOEfyqA9y25TcjLtDnjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2901f6031ee0bf8ef997e964179f664673b81ef59b731a22cdf7cc0b0dd8a366","last_reissued_at":"2026-05-17T23:45:48.667596Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.667596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07727","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JB/O09vK8gmoF56zkZcO7/wgkcj007TKS+IOggmf4aBIf1y5xlC2qce3NXBtK7/Z/6fLAAkd9qhp/4lYBlDlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:33:06.051762Z"},"content_sha256":"ac6b5b21a105e55919dbfd3f7421f4946292dcc2908f2a6343a2a74c8b6a248c","schema_version":"1.0","event_id":"sha256:ac6b5b21a105e55919dbfd3f7421f4946292dcc2908f2a6343a2a74c8b6a248c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FEA7MAY64C7Y56MX5FSBPH3GIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Learning of Dynamical Systems in Uncertain Environment: a Tutorial","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mehran Attar, Mohammadreza Dabirian","submitted_at":"2019-05-19T11:29:01Z","abstract_excerpt":"In this paper, a review of model-free reinforcement learning for learning of dynamical systems in uncertain environments has discussed. For this purpose, the Markov Decision Process (MDP) will be reviewed. Furthermore, some learning algorithms such as Temporal Difference (TD) learning, Q-Learning, and Approximate Q-learning as model-free algorithms which constitute the main part of this article have been investigated, and benefits and drawbacks of each algorithm will be discussed. The discussed concepts in each section are explaining with details and examples."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07727","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzbAmJRAlSWQsql/tG3JdgR9iBMBxiMsBceg4LJzOe8T2oD098nVJ0rlyvW9flP9tgKEL+iGyiVirqc/S8ZcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:33:06.052133Z"},"content_sha256":"b86e8337d7734a8493f3db93f6e98f3c228ec60051473c8bbb97bdedccafba38","schema_version":"1.0","event_id":"sha256:b86e8337d7734a8493f3db93f6e98f3c228ec60051473c8bbb97bdedccafba38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/bundle.json","state_url":"https://pith.science/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/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":"2026-06-30T02:33:06Z","links":{"resolver":"https://pith.science/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ","bundle":"https://pith.science/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/bundle.json","state":"https://pith.science/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEA7MAY64C7Y56MX5FSBPH3GIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FEA7MAY64C7Y56MX5FSBPH3GIZ","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":"58451b68a3c3e3b5876b8f5634a887a982f776d4308bf43997457e3c4cdc7082","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T11:29:01Z","title_canon_sha256":"dfa56c1098b24e0c259a6d4b5a5f6c701f3a35bb98ef008cd64e1a728f37db4e"},"schema_version":"1.0","source":{"id":"1905.07727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07727","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07727v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07727","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"FEA7MAY64C7Y","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FEA7MAY64C7Y56MX","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FEA7MAY6","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:b86e8337d7734a8493f3db93f6e98f3c228ec60051473c8bbb97bdedccafba38","target":"graph","created_at":"2026-05-17T23:45:48Z","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":"In this paper, a review of model-free reinforcement learning for learning of dynamical systems in uncertain environments has discussed. For this purpose, the Markov Decision Process (MDP) will be reviewed. Furthermore, some learning algorithms such as Temporal Difference (TD) learning, Q-Learning, and Approximate Q-learning as model-free algorithms which constitute the main part of this article have been investigated, and benefits and drawbacks of each algorithm will be discussed. The discussed concepts in each section are explaining with details and examples.","authors_text":"Mehran Attar, Mohammadreza Dabirian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T11:29:01Z","title":"Reinforcement Learning for Learning of Dynamical Systems in Uncertain Environment: a Tutorial"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07727","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:ac6b5b21a105e55919dbfd3f7421f4946292dcc2908f2a6343a2a74c8b6a248c","target":"record","created_at":"2026-05-17T23:45:48Z","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":"58451b68a3c3e3b5876b8f5634a887a982f776d4308bf43997457e3c4cdc7082","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T11:29:01Z","title_canon_sha256":"dfa56c1098b24e0c259a6d4b5a5f6c701f3a35bb98ef008cd64e1a728f37db4e"},"schema_version":"1.0","source":{"id":"1905.07727","kind":"arxiv","version":1}},"canonical_sha256":"2901f6031ee0bf8ef997e964179f664673b81ef59b731a22cdf7cc0b0dd8a366","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2901f6031ee0bf8ef997e964179f664673b81ef59b731a22cdf7cc0b0dd8a366","first_computed_at":"2026-05-17T23:45:48.667596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.667596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AKSR2BhN7Jx3GmgPpEtJRA4Wbk8rD3fWjNC50rjKFca5wtwMcA8pvPR1yhSVBlDSxiOEfyqA9y25TcjLtDnjCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.668161Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac6b5b21a105e55919dbfd3f7421f4946292dcc2908f2a6343a2a74c8b6a248c","sha256:b86e8337d7734a8493f3db93f6e98f3c228ec60051473c8bbb97bdedccafba38"],"state_sha256":"b579b1705f441e89e2ddb0db7ba42bb99cf45bed01e43884ba9eb452de1b8295"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsQPzSU0bSrLOpsdaIIbmbhRkvJjgqbj3e21JWwoM4/1arRiQxvEZvXaVi8iFBJFIb0PmZgpPmYhte+yIyNKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T02:33:06.054555Z","bundle_sha256":"61e548e30a63afe0ec501fa1c38dee72b3bb09e3a4f9db97ca4fce72810f3f5e"}}