{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:R6BET6LIN64JQ7LVI3ULIORNDA","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":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba"},"schema_version":"1.0","source":{"id":"1611.07078","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07078v2","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"R6BET6LIN64J","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"R6BET6LIN64JQ7LV","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"R6BET6LI","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931","target":"graph","created_at":"2026-05-18T00:37:54Z","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":"Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment.\n  In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating","authors_text":"Felix Leibfried, Katja Hofmann, Nate Kushman","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title":"A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07078","kind":"arxiv","version":2},"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:b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352","target":"record","created_at":"2026-05-18T00:37:54Z","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":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba"},"schema_version":"1.0","source":{"id":"1611.07078","kind":"arxiv","version":2}},"canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","first_computed_at":"2026-05-18T00:37:54.711091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:54.711091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g/SJt4g0+F1xb2hFZOdt9XInjlpF1V6HrB8ifD0rgWhBK/MkWZauRcDZnNQ1KvCvz19gThwqWIxgajw4DvRkAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:54.711616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.07078","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352","sha256:a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931"],"state_sha256":"61a23002ae5aa94fadafc80a06635c0f222b2603ab11ec1c8c2e0e5d017a2e53"}