{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XA7J4FAA6YL5MJGXI7WJYIEICH","short_pith_number":"pith:XA7J4FAA","schema_version":"1.0","canonical_sha256":"b83e9e1400f617d624d747ec9c208811fda09a6252fd7401bee843483ffe45dc","source":{"kind":"arxiv","id":"1705.07445","version":2},"attestation_state":"computed","paper":{"title":"Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Girish Raguvir J, Sahil Sharma, Srivatsan Ramesh","submitted_at":"2017-05-21T12:47:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1705.07445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-21T12:47:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5589b18c6ba7adff0c993d2e70bd4aca093fd7e73882716908e3e75deb84a3eb","abstract_canon_sha256":"3a88791795c1326771b0541c8ccd8325e8bdb4cc3e11a287a756e9d6201c2f68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.477067Z","signature_b64":"O84Q+PmDSjulcf7k5UEEVBNDNN78oyMli7B1xUPQ1Enlkd9IfU0H57EbeOpeQDh4Ftj8IX0DEsFtaV84W1xGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83e9e1400f617d624d747ec9c208811fda09a6252fd7401bee843483ffe45dc","last_reissued_at":"2026-05-18T00:31:19.476438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.476438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Girish Raguvir J, Sahil Sharma, Srivatsan Ramesh","submitted_at":"2017-05-21T12:47:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07445","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.07445","created_at":"2026-05-18T00:31:19.476542+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07445v2","created_at":"2026-05-18T00:31:19.476542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07445","created_at":"2026-05-18T00:31:19.476542+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA7J4FAA6YL5","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA7J4FAA6YL5MJGX","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA7J4FAA","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":190,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH","json":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH.json","graph_json":"https://pith.science/api/pith-number/XA7J4FAA6YL5MJGXI7WJYIEICH/graph.json","events_json":"https://pith.science/api/pith-number/XA7J4FAA6YL5MJGXI7WJYIEICH/events.json","paper":"https://pith.science/paper/XA7J4FAA"},"agent_actions":{"view_html":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH","download_json":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH.json","view_paper":"https://pith.science/paper/XA7J4FAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07445&json=true","fetch_graph":"https://pith.science/api/pith-number/XA7J4FAA6YL5MJGXI7WJYIEICH/graph.json","fetch_events":"https://pith.science/api/pith-number/XA7J4FAA6YL5MJGXI7WJYIEICH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH/action/storage_attestation","attest_author":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH/action/author_attestation","sign_citation":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH/action/citation_signature","submit_replication":"https://pith.science/pith/XA7J4FAA6YL5MJGXI7WJYIEICH/action/replication_record"}},"created_at":"2026-05-18T00:31:19.476542+00:00","updated_at":"2026-05-18T00:31:19.476542+00:00"}