{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Y2WI6TZMOB5LOBPTBGYT6UGTTI","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":"2eebe47f992105fe4c0ea7b0c16d4e4967fac7077e8da510ea69bc87c65e8694","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T18:05:48Z","title_canon_sha256":"78597ba42370b3065a53f37b48bbc43aee37c5ad4f3fa9e620fb446a25cdd248"},"schema_version":"1.0","source":{"id":"1706.04208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04208","created_at":"2026-05-18T00:29:30Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04208v2","created_at":"2026-05-18T00:29:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04208","created_at":"2026-05-18T00:29:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y2WI6TZMOB5L","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y2WI6TZMOB5LOBPT","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y2WI6TZM","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:c9f5de73dcfa11971c4030f89dd270299330f285cd6d2fcd83f521049ad46063","target":"graph","created_at":"2026-05-18T00:29:30Z","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":"One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network. While this approach works well in many domains, in domains where the optimal value function cannot easily be reduced to a low-dimensional representation, learning can be very slow and unstable. This paper contributes towards tackling such challenging domains, by proposing a new method, called Hybrid Reward Architecture (HRA). HRA takes as input a decomposed reward function","authors_text":"Harm van Seijen, Jeffrey Tsang, Joshua Romoff, Mehdi Fatemi, Romain Laroche, Tavian Barnes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T18:05:48Z","title":"Hybrid Reward Architecture for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04208","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:beb30063cc8355cd18040a3e8bd05092e7f8d72fea8072c34c58ac5b00373e50","target":"record","created_at":"2026-05-18T00:29:30Z","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":"2eebe47f992105fe4c0ea7b0c16d4e4967fac7077e8da510ea69bc87c65e8694","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T18:05:48Z","title_canon_sha256":"78597ba42370b3065a53f37b48bbc43aee37c5ad4f3fa9e620fb446a25cdd248"},"schema_version":"1.0","source":{"id":"1706.04208","kind":"arxiv","version":2}},"canonical_sha256":"c6ac8f4f2c707ab705f309b13f50d39a291cf9320d4ec65bb84b0f05fcfe87d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6ac8f4f2c707ab705f309b13f50d39a291cf9320d4ec65bb84b0f05fcfe87d5","first_computed_at":"2026-05-18T00:29:30.329426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:30.329426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CvQM+zsC/2Ji4Ra5dx/I6mTwokVlyH3S+AeRf+GhfnoPSnXbXlSd8qTcExL5PuUf4bFgL1YgXE0Px+FTlf2yDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:30.330073Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beb30063cc8355cd18040a3e8bd05092e7f8d72fea8072c34c58ac5b00373e50","sha256:c9f5de73dcfa11971c4030f89dd270299330f285cd6d2fcd83f521049ad46063"],"state_sha256":"9e9a15e887893b7db637d1d957897ab4a8ff49dfbb89ca8bf0369eb6c2349603"}