{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XA7J4FAA6YL5MJGXI7WJYIEICH","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":"3a88791795c1326771b0541c8ccd8325e8bdb4cc3e11a287a756e9d6201c2f68","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-21T12:47:37Z","title_canon_sha256":"5589b18c6ba7adff0c993d2e70bd4aca093fd7e73882716908e3e75deb84a3eb"},"schema_version":"1.0","source":{"id":"1705.07445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07445","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07445v2","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07445","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"XA7J4FAA6YL5","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XA7J4FAA6YL5MJGX","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XA7J4FAA","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:d8028e31bd74a54186569e40e54cd2edc65a81d1dfd3327c02d29e71d0607706","target":"graph","created_at":"2026-05-18T00:31:19Z","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 (RL) can model complex behavior policies for goal-directed sequential decision making tasks. A hallmark of RL algorithms is Temporal Difference (TD) learning: value function for the current state is moved towards a bootstrapped target that is estimated using next state's value function. $\\lambda$-returns generalize beyond 1-step returns and strike a balance between Monte Carlo and TD learning methods. While lambda-returns have been extensively studied in RL, they haven't been explored a lot in Deep RL. This paper's first contribution is an exhaustive benchmarking of lamb","authors_text":"Balaraman Ravindran, Girish Raguvir J, Sahil Sharma, Srivatsan Ramesh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-21T12:47:37Z","title":"Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07445","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:a5c75cec51f3923063a769fc9136fbbd4e13736da703545228778cb0eac25586","target":"record","created_at":"2026-05-18T00:31:19Z","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":"3a88791795c1326771b0541c8ccd8325e8bdb4cc3e11a287a756e9d6201c2f68","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-21T12:47:37Z","title_canon_sha256":"5589b18c6ba7adff0c993d2e70bd4aca093fd7e73882716908e3e75deb84a3eb"},"schema_version":"1.0","source":{"id":"1705.07445","kind":"arxiv","version":2}},"canonical_sha256":"b83e9e1400f617d624d747ec9c208811fda09a6252fd7401bee843483ffe45dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b83e9e1400f617d624d747ec9c208811fda09a6252fd7401bee843483ffe45dc","first_computed_at":"2026-05-18T00:31:19.476438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:19.476438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O84Q+PmDSjulcf7k5UEEVBNDNN78oyMli7B1xUPQ1Enlkd9IfU0H57EbeOpeQDh4Ftj8IX0DEsFtaV84W1xGBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:19.477067Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c75cec51f3923063a769fc9136fbbd4e13736da703545228778cb0eac25586","sha256:d8028e31bd74a54186569e40e54cd2edc65a81d1dfd3327c02d29e71d0607706"],"state_sha256":"40bbffe55c34192c161d12969272b9a6f8d5f9ab43c7c2d20d17bac9b9189a6d"}