{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4BFKFPLZ7KITI27XE42SQLC5I4","short_pith_number":"pith:4BFKFPLZ","canonical_record":{"source":{"id":"1810.06339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T13:20:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9d8432b56803a36f7d420d40b1d5d3b1a920a5b6b9fb0ca07a1125741639a996","abstract_canon_sha256":"e93d8b7e7d32e28d2e0f0f3bfea89e479332ed4e9fc2276146f3adb5e3124d2b"},"schema_version":"1.0"},"canonical_sha256":"e04aa2bd79fa91346bf72735282c5d47290a71eba1ef1ab4ed1d0966a520d3a7","source":{"kind":"arxiv","id":"1810.06339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06339","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06339v1","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06339","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"4BFKFPLZ7KIT","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4BFKFPLZ7KITI27X","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4BFKFPLZ","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4BFKFPLZ7KITI27XE42SQLC5I4","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T13:20:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9d8432b56803a36f7d420d40b1d5d3b1a920a5b6b9fb0ca07a1125741639a996","abstract_canon_sha256":"e93d8b7e7d32e28d2e0f0f3bfea89e479332ed4e9fc2276146f3adb5e3124d2b"},"schema_version":"1.0"},"canonical_sha256":"e04aa2bd79fa91346bf72735282c5d47290a71eba1ef1ab4ed1d0966a520d3a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:20.775113Z","signature_b64":"OXp8HJPj5BGLGp+7z/TMT0ThoAZYIkEEcQaDZVXCgqXOXncrfhnkl0oFUuyStxcEKTidkR6wABh1/Z75HVtlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04aa2bd79fa91346bf72735282c5d47290a71eba1ef1ab4ed1d0966a520d3a7","last_reissued_at":"2026-05-18T00:03:20.774604Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:20.774604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06339","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":"2026-05-18T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHhoo5gUF5aBWMF9UzYA8gwA6OR4fJP5UC1icQXjlogNMWbzYHLQyPknbXIJfyNFJi1Y17Ydl+8m5w5vp205Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:04:48.446136Z"},"content_sha256":"e18e866d3364ed12693c223a1052c4d3e584524863fe7b41391a5794f1d6e559","schema_version":"1.0","event_id":"sha256:e18e866d3364ed12693c223a1052c4d3e584524863fe7b41391a5794f1d6e559"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4BFKFPLZ7KITI27XE42SQLC5I4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuxi Li","submitted_at":"2018-10-15T13:20:56Z","abstract_excerpt":"We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06339","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":"2026-05-18T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfEC5nhy6G5P+2gnpogm+tUoORbA+nCKzbRtV3hM3+m5CE8HHtZ1L1g/mQeHbtV3ML+8Z8YnpXYPPyM1V49FCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:04:48.446570Z"},"content_sha256":"d955917e4452862414fb8e4c80524aaaf9afe2e341fe03ea72efc1952153d4d0","schema_version":"1.0","event_id":"sha256:d955917e4452862414fb8e4c80524aaaf9afe2e341fe03ea72efc1952153d4d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BFKFPLZ7KITI27XE42SQLC5I4/bundle.json","state_url":"https://pith.science/pith/4BFKFPLZ7KITI27XE42SQLC5I4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BFKFPLZ7KITI27XE42SQLC5I4/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":"2026-05-31T19:04:48Z","links":{"resolver":"https://pith.science/pith/4BFKFPLZ7KITI27XE42SQLC5I4","bundle":"https://pith.science/pith/4BFKFPLZ7KITI27XE42SQLC5I4/bundle.json","state":"https://pith.science/pith/4BFKFPLZ7KITI27XE42SQLC5I4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BFKFPLZ7KITI27XE42SQLC5I4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4BFKFPLZ7KITI27XE42SQLC5I4","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":"e93d8b7e7d32e28d2e0f0f3bfea89e479332ed4e9fc2276146f3adb5e3124d2b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T13:20:56Z","title_canon_sha256":"9d8432b56803a36f7d420d40b1d5d3b1a920a5b6b9fb0ca07a1125741639a996"},"schema_version":"1.0","source":{"id":"1810.06339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06339","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06339v1","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06339","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"4BFKFPLZ7KIT","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4BFKFPLZ7KITI27X","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4BFKFPLZ","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:d955917e4452862414fb8e4c80524aaaf9afe2e341fe03ea72efc1952153d4d0","target":"graph","created_at":"2026-05-18T00:03:20Z","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":"We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervis","authors_text":"Yuxi Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T13:20:56Z","title":"Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06339","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:e18e866d3364ed12693c223a1052c4d3e584524863fe7b41391a5794f1d6e559","target":"record","created_at":"2026-05-18T00:03:20Z","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":"e93d8b7e7d32e28d2e0f0f3bfea89e479332ed4e9fc2276146f3adb5e3124d2b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T13:20:56Z","title_canon_sha256":"9d8432b56803a36f7d420d40b1d5d3b1a920a5b6b9fb0ca07a1125741639a996"},"schema_version":"1.0","source":{"id":"1810.06339","kind":"arxiv","version":1}},"canonical_sha256":"e04aa2bd79fa91346bf72735282c5d47290a71eba1ef1ab4ed1d0966a520d3a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e04aa2bd79fa91346bf72735282c5d47290a71eba1ef1ab4ed1d0966a520d3a7","first_computed_at":"2026-05-18T00:03:20.774604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:20.774604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXp8HJPj5BGLGp+7z/TMT0ThoAZYIkEEcQaDZVXCgqXOXncrfhnkl0oFUuyStxcEKTidkR6wABh1/Z75HVtlDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:20.775113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e18e866d3364ed12693c223a1052c4d3e584524863fe7b41391a5794f1d6e559","sha256:d955917e4452862414fb8e4c80524aaaf9afe2e341fe03ea72efc1952153d4d0"],"state_sha256":"21f4cfb28733c69c2a67ca1c3779e6d7b32ff34427c9937be4391e89c638c1c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GkKoUPG6Zg8KxT1cZqEMJtOP9O1qd7s8ndMwJO1NcKn+zYC4h+0DBt9aV2Tl+mbA4j36XvSD+6Q/v/rnhzlAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:04:48.451126Z","bundle_sha256":"c59bf37668bda6713b8891dd0700bd0a6788a9b6d28b4de6488d0425e3ec8505"}}