{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R6NFOURI26JYVIRUQSDTQNYEGN","short_pith_number":"pith:R6NFOURI","canonical_record":{"source":{"id":"1903.09295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-22T01:41:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"139def92e59bb6fa8072c7f7eb4ef1cd883bb1d20dcc0a2913c0bf50b14b3e52","abstract_canon_sha256":"825d19f099a46577888b2f01ab31b924ca9e84ef7e5bdac9c269a693509c9dfe"},"schema_version":"1.0"},"canonical_sha256":"8f9a575228d7938aa23484873837043352208101e05d7a70677259a5cf56f2e5","source":{"kind":"arxiv","id":"1903.09295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09295","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09295v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09295","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"R6NFOURI26JY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R6NFOURI26JYVIRU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R6NFOURI","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R6NFOURI26JYVIRUQSDTQNYEGN","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-22T01:41:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"139def92e59bb6fa8072c7f7eb4ef1cd883bb1d20dcc0a2913c0bf50b14b3e52","abstract_canon_sha256":"825d19f099a46577888b2f01ab31b924ca9e84ef7e5bdac9c269a693509c9dfe"},"schema_version":"1.0"},"canonical_sha256":"8f9a575228d7938aa23484873837043352208101e05d7a70677259a5cf56f2e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:40.064699Z","signature_b64":"RsfIIrod1Opdh+br8ZeNnpQvnHxEX96GuZQDS/TiERiT/kiNBVpo/GpQcoR1ES6XMJxtJwdBSTabGATtszB0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f9a575228d7938aa23484873837043352208101e05d7a70677259a5cf56f2e5","last_reissued_at":"2026-05-17T23:50:40.064196Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:40.064196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09295","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q31EcxxORhVRm1R1Vz8DDQPhdD0cRtv58jNB5WBozVwZ0f3eyIDa/7fUNuEHt6X+7YxAgWABqimPSD1/RjXLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:48:56.866278Z"},"content_sha256":"3b830bbfed5b467b0b469c0d8db37f97a89e21dd94453d104c396245f740999d","schema_version":"1.0","event_id":"sha256:3b830bbfed5b467b0b469c0d8db37f97a89e21dd94453d104c396245f740999d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R6NFOURI26JYVIRUQSDTQNYEGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DQN with model-based exploration: efficient learning on environments with sparse rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stephen Zhen Gou, Yuyang Liu","submitted_at":"2019-03-22T01:41:50Z","abstract_excerpt":"We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, model-free algorithm and has been proven to perform well in a variety of tasks including Atari 2600 games since it's first proposed by Minh et el. However, like many other reinforcement learning (RL) algorithms, DQN suffers from poor sample efficiency when rewards are sparse in an environment. As a result, most of the transitions stored in the replay memory ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09295","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCO34HWQR1mfg4BoDwGh2miqdVUzugGJDyeA5sB16kP4wf5XhgfrbdybSvuIRBM6mcOM3vx/Jp+06kPIT24sDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:48:56.867042Z"},"content_sha256":"b90b5a34a3b5e73330f2a6f208a05979b55ec42b7aee5b589dc9230dc633ef90","schema_version":"1.0","event_id":"sha256:b90b5a34a3b5e73330f2a6f208a05979b55ec42b7aee5b589dc9230dc633ef90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6NFOURI26JYVIRUQSDTQNYEGN/bundle.json","state_url":"https://pith.science/pith/R6NFOURI26JYVIRUQSDTQNYEGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6NFOURI26JYVIRUQSDTQNYEGN/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":"2026-06-11T08:48:56Z","links":{"resolver":"https://pith.science/pith/R6NFOURI26JYVIRUQSDTQNYEGN","bundle":"https://pith.science/pith/R6NFOURI26JYVIRUQSDTQNYEGN/bundle.json","state":"https://pith.science/pith/R6NFOURI26JYVIRUQSDTQNYEGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6NFOURI26JYVIRUQSDTQNYEGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R6NFOURI26JYVIRUQSDTQNYEGN","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":"825d19f099a46577888b2f01ab31b924ca9e84ef7e5bdac9c269a693509c9dfe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-22T01:41:50Z","title_canon_sha256":"139def92e59bb6fa8072c7f7eb4ef1cd883bb1d20dcc0a2913c0bf50b14b3e52"},"schema_version":"1.0","source":{"id":"1903.09295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09295","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09295v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09295","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"R6NFOURI26JY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R6NFOURI26JYVIRU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R6NFOURI","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b90b5a34a3b5e73330f2a6f208a05979b55ec42b7aee5b589dc9230dc633ef90","target":"graph","created_at":"2026-05-17T23:50:40Z","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 propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, model-free algorithm and has been proven to perform well in a variety of tasks including Atari 2600 games since it's first proposed by Minh et el. However, like many other reinforcement learning (RL) algorithms, DQN suffers from poor sample efficiency when rewards are sparse in an environment. As a result, most of the transitions stored in the replay memory ha","authors_text":"Stephen Zhen Gou, Yuyang Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-22T01:41:50Z","title":"DQN with model-based exploration: efficient learning on environments with sparse rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09295","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":"sha256:3b830bbfed5b467b0b469c0d8db37f97a89e21dd94453d104c396245f740999d","target":"record","created_at":"2026-05-17T23:50:40Z","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":"825d19f099a46577888b2f01ab31b924ca9e84ef7e5bdac9c269a693509c9dfe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-22T01:41:50Z","title_canon_sha256":"139def92e59bb6fa8072c7f7eb4ef1cd883bb1d20dcc0a2913c0bf50b14b3e52"},"schema_version":"1.0","source":{"id":"1903.09295","kind":"arxiv","version":1}},"canonical_sha256":"8f9a575228d7938aa23484873837043352208101e05d7a70677259a5cf56f2e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f9a575228d7938aa23484873837043352208101e05d7a70677259a5cf56f2e5","first_computed_at":"2026-05-17T23:50:40.064196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:40.064196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RsfIIrod1Opdh+br8ZeNnpQvnHxEX96GuZQDS/TiERiT/kiNBVpo/GpQcoR1ES6XMJxtJwdBSTabGATtszB0Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:40.064699Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b830bbfed5b467b0b469c0d8db37f97a89e21dd94453d104c396245f740999d","sha256:b90b5a34a3b5e73330f2a6f208a05979b55ec42b7aee5b589dc9230dc633ef90"],"state_sha256":"4266e6fb82c3b39ec33026ce9a0c1fe41636152f3bbd65433d7d0b3e4f9ce81e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FQCUR93MXrL30QfcZJPZaTNZ3Y/334fnohbiPbRtDTz1xmXy/BApU3CDiEFuoqlMg83JvfeHMZaS7uKpaE8CDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T08:48:56.870962Z","bundle_sha256":"e262653a20129016f402b598d60dca825b60ff494c021c44225b10122052e77e"}}