{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OAGXOCKFVG3HWIDFD4QJI5K5OE","short_pith_number":"pith:OAGXOCKF","canonical_record":{"source":{"id":"1611.00862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T02:28:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c85ca02902261823e1a6ed869dc8a010391fd4717d27686691058ffd6e4135d","abstract_canon_sha256":"e467d38db546cde97775105cd5040fafdc0faffe82dbea7160b22b06e57ab971"},"schema_version":"1.0"},"canonical_sha256":"700d770945a9b67b20651f2094755d712a8f2a411ac7378bf139d7e47691d0e2","source":{"kind":"arxiv","id":"1611.00862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.00862","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"1611.00862v1","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00862","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"OAGXOCKFVG3H","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OAGXOCKFVG3HWIDF","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OAGXOCKF","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OAGXOCKFVG3HWIDFD4QJI5K5OE","target":"record","payload":{"canonical_record":{"source":{"id":"1611.00862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T02:28:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c85ca02902261823e1a6ed869dc8a010391fd4717d27686691058ffd6e4135d","abstract_canon_sha256":"e467d38db546cde97775105cd5040fafdc0faffe82dbea7160b22b06e57ab971"},"schema_version":"1.0"},"canonical_sha256":"700d770945a9b67b20651f2094755d712a8f2a411ac7378bf139d7e47691d0e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:18.488356Z","signature_b64":"UcMVJoOtXr7bf0E8jmajdoZ7tGPgFRNt2s6HcOHWMgslCOUdpcNpHLKq2tHisuaS9U6k+mimaQQHF7cf9XXDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700d770945a9b67b20651f2094755d712a8f2a411ac7378bf139d7e47691d0e2","last_reissued_at":"2026-05-18T01:00:18.487592Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:18.487592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.00862","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":"2026-05-18T01:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSDk3x7wzCAtqaNN9kmUmMV3eMxXJxXsvzXZ2/+AWA3042HUxBHe1PBdwLi6BBbRrWNwZqyPEcAGtSsvaEQaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:18:25.432693Z"},"content_sha256":"e6e0d9897f1fd466b7e8e0b2659e795413a1dbaae292110cf54e40d987830a8b","schema_version":"1.0","event_id":"sha256:e6e0d9897f1fd466b7e8e0b2659e795413a1dbaae292110cf54e40d987830a8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OAGXOCKFVG3HWIDFD4QJI5K5OE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantile Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hugo Gilbert, Paul Weng","submitted_at":"2016-11-03T02:28:53Z","abstract_excerpt":"In reinforcement learning, the standard criterion to evaluate policies in a state is the expectation of (discounted) sum of rewards. However, this criterion may not always be suitable, we consider an alternative criterion based on the notion of quantiles. In the case of episodic reinforcement learning problems, we propose an algorithm based on stochastic approximation with two timescales. We evaluate our proposition on a simple model of the TV show, Who wants to be a millionaire."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00862","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":"2026-05-18T01:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysBCCSl85KRsg+Rma+hNMAINFqAmuIevDpW7kEzVc5rvQhflpDvOIDq2Y1L2XnjCVfmsvv/i6iEqPas4BEhbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:18:25.433595Z"},"content_sha256":"2c8b21c23a51311d5befaf32ee7352d981b8cf2c1eaa6c1ba5521cabbdf86785","schema_version":"1.0","event_id":"sha256:2c8b21c23a51311d5befaf32ee7352d981b8cf2c1eaa6c1ba5521cabbdf86785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/bundle.json","state_url":"https://pith.science/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/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":"2026-05-25T19:18:25Z","links":{"resolver":"https://pith.science/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE","bundle":"https://pith.science/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/bundle.json","state":"https://pith.science/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAGXOCKFVG3HWIDFD4QJI5K5OE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OAGXOCKFVG3HWIDFD4QJI5K5OE","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":"e467d38db546cde97775105cd5040fafdc0faffe82dbea7160b22b06e57ab971","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T02:28:53Z","title_canon_sha256":"4c85ca02902261823e1a6ed869dc8a010391fd4717d27686691058ffd6e4135d"},"schema_version":"1.0","source":{"id":"1611.00862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.00862","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"1611.00862v1","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00862","created_at":"2026-05-18T01:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"OAGXOCKFVG3H","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OAGXOCKFVG3HWIDF","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OAGXOCKF","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:2c8b21c23a51311d5befaf32ee7352d981b8cf2c1eaa6c1ba5521cabbdf86785","target":"graph","created_at":"2026-05-18T01:00:18Z","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":"In reinforcement learning, the standard criterion to evaluate policies in a state is the expectation of (discounted) sum of rewards. However, this criterion may not always be suitable, we consider an alternative criterion based on the notion of quantiles. In the case of episodic reinforcement learning problems, we propose an algorithm based on stochastic approximation with two timescales. We evaluate our proposition on a simple model of the TV show, Who wants to be a millionaire.","authors_text":"Hugo Gilbert, Paul Weng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T02:28:53Z","title":"Quantile Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00862","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:e6e0d9897f1fd466b7e8e0b2659e795413a1dbaae292110cf54e40d987830a8b","target":"record","created_at":"2026-05-18T01:00:18Z","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":"e467d38db546cde97775105cd5040fafdc0faffe82dbea7160b22b06e57ab971","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T02:28:53Z","title_canon_sha256":"4c85ca02902261823e1a6ed869dc8a010391fd4717d27686691058ffd6e4135d"},"schema_version":"1.0","source":{"id":"1611.00862","kind":"arxiv","version":1}},"canonical_sha256":"700d770945a9b67b20651f2094755d712a8f2a411ac7378bf139d7e47691d0e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"700d770945a9b67b20651f2094755d712a8f2a411ac7378bf139d7e47691d0e2","first_computed_at":"2026-05-18T01:00:18.487592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:18.487592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UcMVJoOtXr7bf0E8jmajdoZ7tGPgFRNt2s6HcOHWMgslCOUdpcNpHLKq2tHisuaS9U6k+mimaQQHF7cf9XXDCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:18.488356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.00862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6e0d9897f1fd466b7e8e0b2659e795413a1dbaae292110cf54e40d987830a8b","sha256:2c8b21c23a51311d5befaf32ee7352d981b8cf2c1eaa6c1ba5521cabbdf86785"],"state_sha256":"c0860180fdc28aa9f34da5cadbaec4af3756f958d90d6b54ba16a29cdacff595"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Va884cyk4pwu9DYS+IGqJIgq0PNfoEoccgIbYVT9QpE1L+Ir4UUDpq5JSKQb7dDO3PvsfiDaHUgGuCVPFv/yAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:18:25.438145Z","bundle_sha256":"aaecc4228dcb628eed3dfa5da5fdeabe42934685c219606a9f161f8878fdb386"}}