{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SHSAYRXLBNDFZGAAQEXRJ4B3V3","short_pith_number":"pith:SHSAYRXL","canonical_record":{"source":{"id":"1701.07274","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T11:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b","abstract_canon_sha256":"58076a00f8fa9537db8958b0bcbf58bbf8bd59f94ab77ca35bc296166812c937"},"schema_version":"1.0"},"canonical_sha256":"91e40c46eb0b465c9800812f14f03baed634902f4c33741f9decbe2366ff9bdd","source":{"kind":"arxiv","id":"1701.07274","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.07274","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1701.07274v6","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.07274","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"SHSAYRXLBNDF","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SHSAYRXLBNDFZGAA","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SHSAYRXL","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SHSAYRXLBNDFZGAAQEXRJ4B3V3","target":"record","payload":{"canonical_record":{"source":{"id":"1701.07274","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T11:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b","abstract_canon_sha256":"58076a00f8fa9537db8958b0bcbf58bbf8bd59f94ab77ca35bc296166812c937"},"schema_version":"1.0"},"canonical_sha256":"91e40c46eb0b465c9800812f14f03baed634902f4c33741f9decbe2366ff9bdd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:02.625190Z","signature_b64":"F8vOTSHQ2KHShSrVQ9AT+2ZLFN8wdsdvQ1fj441WScTYzCPmRhtJjxnPFyS6rqdJLXINT/BL7+hYQkiH2NZWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91e40c46eb0b465c9800812f14f03baed634902f4c33741f9decbe2366ff9bdd","last_reissued_at":"2026-05-18T00:00:02.624772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:02.624772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.07274","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtHUnc/PqJLObov+5llCUmLCTpMvC9V64ashWaidtnQZp5MhciPjN7J92vuR2SCVPbRa/BC8BLadUEX2LagvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:47.967964Z"},"content_sha256":"3367452db6aae5114fd8c16fcfebe976f35cd18a3513ac6fc03824cc2b5d08af","schema_version":"1.0","event_id":"sha256:3367452db6aae5114fd8c16fcfebe976f35cd18a3513ac6fc03824cc2b5d08af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SHSAYRXLBNDFZGAAQEXRJ4B3V3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning: An Overview","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yuxi Li","submitted_at":"2017-01-25T11:52:11Z","abstract_excerpt":"We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn. Then we discu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.07274","kind":"arxiv","version":6},"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":"2026-05-18T00:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aHlcWuUdIzYRGgQQZ3BT+z2H1lZJiPSn1PLmoRI7CUMLoovA5s8/afAPm7PJc2TTX1IhepPvrHwRtZDchMIWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:47.968326Z"},"content_sha256":"856345f0d148a83e46eab30fdf47db68b2abbe2363f41638f2d1eb1e71e97deb","schema_version":"1.0","event_id":"sha256:856345f0d148a83e46eab30fdf47db68b2abbe2363f41638f2d1eb1e71e97deb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/bundle.json","state_url":"https://pith.science/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/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":"2026-05-30T08:40:47Z","links":{"resolver":"https://pith.science/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3","bundle":"https://pith.science/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/bundle.json","state":"https://pith.science/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHSAYRXLBNDFZGAAQEXRJ4B3V3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SHSAYRXLBNDFZGAAQEXRJ4B3V3","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":"58076a00f8fa9537db8958b0bcbf58bbf8bd59f94ab77ca35bc296166812c937","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T11:52:11Z","title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b"},"schema_version":"1.0","source":{"id":"1701.07274","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.07274","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1701.07274v6","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.07274","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"SHSAYRXLBNDF","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SHSAYRXLBNDFZGAA","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SHSAYRXL","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:856345f0d148a83e46eab30fdf47db68b2abbe2363f41638f2d1eb1e71e97deb","target":"graph","created_at":"2026-05-18T00:00:02Z","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 give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn. Then we discu","authors_text":"Yuxi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T11:52:11Z","title":"Deep Reinforcement Learning: An Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.07274","kind":"arxiv","version":6},"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":"sha256:3367452db6aae5114fd8c16fcfebe976f35cd18a3513ac6fc03824cc2b5d08af","target":"record","created_at":"2026-05-18T00:00:02Z","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":"58076a00f8fa9537db8958b0bcbf58bbf8bd59f94ab77ca35bc296166812c937","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T11:52:11Z","title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b"},"schema_version":"1.0","source":{"id":"1701.07274","kind":"arxiv","version":6}},"canonical_sha256":"91e40c46eb0b465c9800812f14f03baed634902f4c33741f9decbe2366ff9bdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91e40c46eb0b465c9800812f14f03baed634902f4c33741f9decbe2366ff9bdd","first_computed_at":"2026-05-18T00:00:02.624772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:02.624772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8vOTSHQ2KHShSrVQ9AT+2ZLFN8wdsdvQ1fj441WScTYzCPmRhtJjxnPFyS6rqdJLXINT/BL7+hYQkiH2NZWBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:02.625190Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.07274","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3367452db6aae5114fd8c16fcfebe976f35cd18a3513ac6fc03824cc2b5d08af","sha256:856345f0d148a83e46eab30fdf47db68b2abbe2363f41638f2d1eb1e71e97deb"],"state_sha256":"54f1bdddecf5b4bf6e782e017365677322ef8c7b438a1d1e5a88cfecbf4b30f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfTR3w5npwYK0h9wXjSI9XfVzQkqsczZOi8CoXkOmtaH6tcEwOje4Pj7Bj+dPs0KyB7OJ5+760LksJsckK/rAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:40:47.970570Z","bundle_sha256":"feba4a53cf70cd6cdcf47d7a0902efa91ca12a6108b3f55c5d179847ce9fcaa5"}}