{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XPJT74A556ZMM7EH2UYWEIAYX4","short_pith_number":"pith:XPJT74A5","canonical_record":{"source":{"id":"2007.14430","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-28T18:30:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ebf7b64dc5758385f96bfb96d71babb8836af7c19c27934e171f9ac90a07c22","abstract_canon_sha256":"463f677d698a949ccaac2dafceb06b583689fe8711dbe606d308919adf76cb1b"},"schema_version":"1.0"},"canonical_sha256":"bbd33ff01defb2c67c87d531622018bf3fdfec3bec3998f10fada3ff59e4025f","source":{"kind":"arxiv","id":"2007.14430","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14430","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14430v3","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14430","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"XPJT74A556ZM","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"XPJT74A556ZMM7EH","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"XPJT74A5","created_at":"2026-07-05T01:49:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XPJT74A556ZMM7EH2UYWEIAYX4","target":"record","payload":{"canonical_record":{"source":{"id":"2007.14430","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-28T18:30:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ebf7b64dc5758385f96bfb96d71babb8836af7c19c27934e171f9ac90a07c22","abstract_canon_sha256":"463f677d698a949ccaac2dafceb06b583689fe8711dbe606d308919adf76cb1b"},"schema_version":"1.0"},"canonical_sha256":"bbd33ff01defb2c67c87d531622018bf3fdfec3bec3998f10fada3ff59e4025f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:04.584977Z","signature_b64":"EnqxHs+jvGUlYa8y/VtZWtpAG1SBN5hm4S6bf7djQJlM8hQlI6ipjZJYyQAHBXOoptEPI+gcoZguZPT7fpGQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd33ff01defb2c67c87d531622018bf3fdfec3bec3998f10fada3ff59e4025f","last_reissued_at":"2026-07-05T01:49:04.584523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:04.584523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.14430","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:49:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TUGErXuaLL3zvG4HqlGTHnLXDGukcO1NHn4O/w4JAvadWUXCY+sMZnaGDrlEhzYhBp7iCJIlN4qnvc3JlfpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:47:12.394498Z"},"content_sha256":"3b4c915daffc0ce3ab861c92d9e018dc046e838021b248c3745241623115f3ee","schema_version":"1.0","event_id":"sha256:3b4c915daffc0ce3ab861c92d9e018dc046e838021b248c3745241623115f3ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XPJT74A556ZMM7EH2UYWEIAYX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Munchausen Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthieu Geist, Nino Vieillard, Olivier Pietquin","submitted_at":"2020-07-28T18:30:23Z","abstract_excerpt":"Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged to bootstrap RL: the current policy. Our core contribution stands in a very simple idea: adding the scaled log-policy to the immediate reward. We show that slightly modifying Deep Q-Network (DQN) in that way provides an agent that is competitive with distributional methods on Atari games, without making use of distributional RL, n-step returns or prioritize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14430","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.14430/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:49:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbXJFKobCzi77lCaM0efi2NmGf8zDGBD6Vrs9pjr3YVlMgljf6kA35LidOlxndn4AOMkQAIoxSUI5CBwcNDLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:47:12.394995Z"},"content_sha256":"56688d8f2ea32873f03c3a0e2540d2d7573e65185bfa5616110d0e658ec82769","schema_version":"1.0","event_id":"sha256:56688d8f2ea32873f03c3a0e2540d2d7573e65185bfa5616110d0e658ec82769"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPJT74A556ZMM7EH2UYWEIAYX4/bundle.json","state_url":"https://pith.science/pith/XPJT74A556ZMM7EH2UYWEIAYX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPJT74A556ZMM7EH2UYWEIAYX4/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":"2026-08-09T23:47:12Z","links":{"resolver":"https://pith.science/pith/XPJT74A556ZMM7EH2UYWEIAYX4","bundle":"https://pith.science/pith/XPJT74A556ZMM7EH2UYWEIAYX4/bundle.json","state":"https://pith.science/pith/XPJT74A556ZMM7EH2UYWEIAYX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPJT74A556ZMM7EH2UYWEIAYX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XPJT74A556ZMM7EH2UYWEIAYX4","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":"463f677d698a949ccaac2dafceb06b583689fe8711dbe606d308919adf76cb1b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-28T18:30:23Z","title_canon_sha256":"7ebf7b64dc5758385f96bfb96d71babb8836af7c19c27934e171f9ac90a07c22"},"schema_version":"1.0","source":{"id":"2007.14430","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14430","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14430v3","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14430","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"XPJT74A556ZM","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"XPJT74A556ZMM7EH","created_at":"2026-07-05T01:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"XPJT74A5","created_at":"2026-07-05T01:49:04Z"}],"graph_snapshots":[{"event_id":"sha256:56688d8f2ea32873f03c3a0e2540d2d7573e65185bfa5616110d0e658ec82769","target":"graph","created_at":"2026-07-05T01:49:04Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.14430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged to bootstrap RL: the current policy. Our core contribution stands in a very simple idea: adding the scaled log-policy to the immediate reward. We show that slightly modifying Deep Q-Network (DQN) in that way provides an agent that is competitive with distributional methods on Atari games, without making use of distributional RL, n-step returns or prioritize","authors_text":"Matthieu Geist, Nino Vieillard, Olivier Pietquin","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-28T18:30:23Z","title":"Munchausen Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14430","kind":"arxiv","version":3},"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":"sha256:3b4c915daffc0ce3ab861c92d9e018dc046e838021b248c3745241623115f3ee","target":"record","created_at":"2026-07-05T01:49:04Z","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":"463f677d698a949ccaac2dafceb06b583689fe8711dbe606d308919adf76cb1b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-28T18:30:23Z","title_canon_sha256":"7ebf7b64dc5758385f96bfb96d71babb8836af7c19c27934e171f9ac90a07c22"},"schema_version":"1.0","source":{"id":"2007.14430","kind":"arxiv","version":3}},"canonical_sha256":"bbd33ff01defb2c67c87d531622018bf3fdfec3bec3998f10fada3ff59e4025f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd33ff01defb2c67c87d531622018bf3fdfec3bec3998f10fada3ff59e4025f","first_computed_at":"2026-07-05T01:49:04.584523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:04.584523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EnqxHs+jvGUlYa8y/VtZWtpAG1SBN5hm4S6bf7djQJlM8hQlI6ipjZJYyQAHBXOoptEPI+gcoZguZPT7fpGQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:04.584977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.14430","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b4c915daffc0ce3ab861c92d9e018dc046e838021b248c3745241623115f3ee","sha256:56688d8f2ea32873f03c3a0e2540d2d7573e65185bfa5616110d0e658ec82769"],"state_sha256":"0d1ee879ac7b8c070d12a204d232da7200ba77a8a6c410c74daa508ae5f9943d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JOejj5uOWnB5kb+u0OaDAzbrCa+sHR4UOVUvGvSHORyUH8LIIfgObB0BOaZ7r2idUFObOSHuNTeIYEweKsTJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:47:12.398242Z","bundle_sha256":"ef88368a3ca0338e7d9a931a2de41934cbcc5860e19b72a07166a92bddc25a91"}}