{"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"}