{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IBNWYLZPA6AZIJ6FWXVDGNGCZR","short_pith_number":"pith:IBNWYLZP","canonical_record":{"source":{"id":"1905.06125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T19:08:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"52e677d89d14e15b66965b453c62c91bf04a4e69bed8b571f3900b0f48b52c8f","abstract_canon_sha256":"c742c0765477aafbf945cf046b6419f0e09800f16143f529fd822799636353f4"},"schema_version":"1.0"},"canonical_sha256":"405b6c2f2f07819427c5b5ea3334c2cc4385ed561695eb1956269f0283ad6920","source":{"kind":"arxiv","id":"1905.06125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06125","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06125v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06125","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"IBNWYLZPA6AZ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IBNWYLZPA6AZIJ6F","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IBNWYLZP","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IBNWYLZPA6AZIJ6FWXVDGNGCZR","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T19:08:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"52e677d89d14e15b66965b453c62c91bf04a4e69bed8b571f3900b0f48b52c8f","abstract_canon_sha256":"c742c0765477aafbf945cf046b6419f0e09800f16143f529fd822799636353f4"},"schema_version":"1.0"},"canonical_sha256":"405b6c2f2f07819427c5b5ea3334c2cc4385ed561695eb1956269f0283ad6920","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:07.389878Z","signature_b64":"Bd76jYpDmFo9sPz6EUQ19lCgK+HSoUtCPgsi6vOYDp00f+bCohF0CMDRWxErpBlVckQgqdwySc5TxUnSV+uLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405b6c2f2f07819427c5b5ea3334c2cc4385ed561695eb1956269f0283ad6920","last_reissued_at":"2026-05-17T23:46:07.389151Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:07.389151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06125","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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqABn7abiq6jezKJwiGR/cOFaJV30mm+Pe/YKUC65OYUAk0o5EY99zE+vPbxIMYqi3EwlLfAFfQtXryTf9shCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:34:42.864839Z"},"content_sha256":"29a6c02bc49f24b9b435ac29aade7461aadffc1e6ea2187b6191259001fcb55d","schema_version":"1.0","event_id":"sha256:29a6c02bc49f24b9b435ac29aade7461aadffc1e6ea2187b6191259001fcb55d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IBNWYLZPA6AZIJ6FWXVDGNGCZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Reinforcement Learning for Efficient Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Borislav Mavrin, Hengshuai Yao, Kaiwen Wu, Linglong Kong, Shangtong Zhang, Yaoliang Yu","submitted_at":"2019-05-13T19:08:55Z","abstract_excerpt":"In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The first is a decaying schedule to suppress the intrinsic uncertainty. The second is an exploration bonus calculated from the upper quantiles of the learned distribution. In Atari 2600 games, our method outperforms QR-DQN in 12 out of 14 hard games (achieving 483 \\% average gain across 49 games in cumulative rewards over QR-DQN with a big win in Venture). We a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06125","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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7egUdjwsHQaGynQUpRP+v8/0IM2/aBRSURAOqZH3M1xu2jPfDagGPOjY1XuU0ln++tyObbP+Xnl7f109cDNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:34:42.865408Z"},"content_sha256":"1837aff4861a7f2044169e678ab0fe6d25e1e44bb71148382147bb2b07845e10","schema_version":"1.0","event_id":"sha256:1837aff4861a7f2044169e678ab0fe6d25e1e44bb71148382147bb2b07845e10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/bundle.json","state_url":"https://pith.science/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/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":"2026-06-05T00:34:42Z","links":{"resolver":"https://pith.science/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR","bundle":"https://pith.science/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/bundle.json","state":"https://pith.science/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBNWYLZPA6AZIJ6FWXVDGNGCZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IBNWYLZPA6AZIJ6FWXVDGNGCZR","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":"c742c0765477aafbf945cf046b6419f0e09800f16143f529fd822799636353f4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T19:08:55Z","title_canon_sha256":"52e677d89d14e15b66965b453c62c91bf04a4e69bed8b571f3900b0f48b52c8f"},"schema_version":"1.0","source":{"id":"1905.06125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06125","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06125v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06125","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"IBNWYLZPA6AZ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IBNWYLZPA6AZIJ6F","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IBNWYLZP","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:1837aff4861a7f2044169e678ab0fe6d25e1e44bb71148382147bb2b07845e10","target":"graph","created_at":"2026-05-17T23:46:07Z","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 distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The first is a decaying schedule to suppress the intrinsic uncertainty. The second is an exploration bonus calculated from the upper quantiles of the learned distribution. In Atari 2600 games, our method outperforms QR-DQN in 12 out of 14 hard games (achieving 483 \\% average gain across 49 games in cumulative rewards over QR-DQN with a big win in Venture). We a","authors_text":"Borislav Mavrin, Hengshuai Yao, Kaiwen Wu, Linglong Kong, Shangtong Zhang, Yaoliang Yu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T19:08:55Z","title":"Distributional Reinforcement Learning for Efficient Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06125","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":"sha256:29a6c02bc49f24b9b435ac29aade7461aadffc1e6ea2187b6191259001fcb55d","target":"record","created_at":"2026-05-17T23:46:07Z","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":"c742c0765477aafbf945cf046b6419f0e09800f16143f529fd822799636353f4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T19:08:55Z","title_canon_sha256":"52e677d89d14e15b66965b453c62c91bf04a4e69bed8b571f3900b0f48b52c8f"},"schema_version":"1.0","source":{"id":"1905.06125","kind":"arxiv","version":1}},"canonical_sha256":"405b6c2f2f07819427c5b5ea3334c2cc4385ed561695eb1956269f0283ad6920","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"405b6c2f2f07819427c5b5ea3334c2cc4385ed561695eb1956269f0283ad6920","first_computed_at":"2026-05-17T23:46:07.389151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:07.389151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bd76jYpDmFo9sPz6EUQ19lCgK+HSoUtCPgsi6vOYDp00f+bCohF0CMDRWxErpBlVckQgqdwySc5TxUnSV+uLAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:07.389878Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29a6c02bc49f24b9b435ac29aade7461aadffc1e6ea2187b6191259001fcb55d","sha256:1837aff4861a7f2044169e678ab0fe6d25e1e44bb71148382147bb2b07845e10"],"state_sha256":"401775598a51b0654f099c703e9b48b66c3e3b721916782b0f44cbbd6325cb98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQ0NXnL53puescrJuJ4y22Br1iOle6+iYcIdeSvxptlOPRijEGkUNngwCuetrxA+UNygno8bBS04F4jdpPyHAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:34:42.868383Z","bundle_sha256":"bcf82a45f20eaa7c0ac419a6c43a01474a5b6c24865bdf848c30a663f0d4d63f"}}