{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NJ524Y4J6N53772Z2RELQZ3I2O","short_pith_number":"pith:NJ524Y4J","canonical_record":{"source":{"id":"2411.14085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T12:51:09Z","cross_cats_sorted":[],"title_canon_sha256":"f1b046c1c0c84cd57a579fb2fd69d741a03607aae2137ceb98d20a9850efce9b","abstract_canon_sha256":"aff435edcb603373034fad6392f3824d2a3a63ba5078391a35d33466ec963838"},"schema_version":"1.0"},"canonical_sha256":"6a7bae6389f37bbfff59d448b86768d3a87e7c5a9dfa2e0da4941c0251431f02","source":{"kind":"arxiv","id":"2411.14085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14085","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14085v1","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14085","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"NJ524Y4J6N53","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"NJ524Y4J6N53772Z","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"NJ524Y4J","created_at":"2026-07-05T09:38:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NJ524Y4J6N53772Z2RELQZ3I2O","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T12:51:09Z","cross_cats_sorted":[],"title_canon_sha256":"f1b046c1c0c84cd57a579fb2fd69d741a03607aae2137ceb98d20a9850efce9b","abstract_canon_sha256":"aff435edcb603373034fad6392f3824d2a3a63ba5078391a35d33466ec963838"},"schema_version":"1.0"},"canonical_sha256":"6a7bae6389f37bbfff59d448b86768d3a87e7c5a9dfa2e0da4941c0251431f02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:41.462949Z","signature_b64":"d9rI1Fa8zGvXQ9vU2kRFp+OiSXzE7tAuyJvNpWTaXMxyq1g/Gph/XpPbj2Y7+8NpEdly3hZAnt9sRYzHjmsVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7bae6389f37bbfff59d448b86768d3a87e7c5a9dfa2e0da4941c0251431f02","last_reissued_at":"2026-07-05T09:38:41.462538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:41.462538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14085","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":"2026-07-05T09:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtMCa6EOhWqs4xjhJRrEs8gWRsB1T80f8jDSMzOZ2+CbHnu+9tQG4uxYyYuwJdeTZgyQSGqui6YrbyQH5epWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:52.481555Z"},"content_sha256":"38a64e00419302f842360ecfe5b2f20c8476451f6e32924632c7ba5cd5f4889c","schema_version":"1.0","event_id":"sha256:38a64e00419302f842360ecfe5b2f20c8476451f6e32924632c7ba5cd5f4889c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NJ524Y4J6N53772Z2RELQZ3I2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration by Running Away from the Past","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dennis G. Wilson, Emmanuel Rachelson, Florent Teichteil-Koenigsbuch, Paul-Antoine Le Tolguenec, Yann Besse","submitted_at":"2024-11-21T12:51:09Z","abstract_excerpt":"The ability to explore efficiently and effectively is a central challenge of reinforcement learning. In this work, we consider exploration through the lens of information theory. Specifically, we cast exploration as a problem of maximizing the Shannon entropy of the state occupation measure. This is done by maximizing a sequence of divergences between distributions representing an agent's past behavior and its current behavior. Intuitively, this encourages the agent to explore new behaviors that are distinct from past behaviors. Hence, we call our method RAMP, for ``$\\textbf{R}$unning $\\textbf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14085","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.14085/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":"2026-07-05T09:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VoZn7640MnJiqRN8It1CiLsGcRKFnMuehi0fgEzMbpkNEQao8lhrjmPY1hz/PgqxM4Vea6F1C6bjLJfseO/PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:52.482087Z"},"content_sha256":"2f6b76cf53eacc0311fc13fbd3a430628ab4f07ede428efe658206e34863faa0","schema_version":"1.0","event_id":"sha256:2f6b76cf53eacc0311fc13fbd3a430628ab4f07ede428efe658206e34863faa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJ524Y4J6N53772Z2RELQZ3I2O/bundle.json","state_url":"https://pith.science/pith/NJ524Y4J6N53772Z2RELQZ3I2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJ524Y4J6N53772Z2RELQZ3I2O/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":"2026-08-12T23:17:52Z","links":{"resolver":"https://pith.science/pith/NJ524Y4J6N53772Z2RELQZ3I2O","bundle":"https://pith.science/pith/NJ524Y4J6N53772Z2RELQZ3I2O/bundle.json","state":"https://pith.science/pith/NJ524Y4J6N53772Z2RELQZ3I2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJ524Y4J6N53772Z2RELQZ3I2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJ524Y4J6N53772Z2RELQZ3I2O","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":"aff435edcb603373034fad6392f3824d2a3a63ba5078391a35d33466ec963838","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T12:51:09Z","title_canon_sha256":"f1b046c1c0c84cd57a579fb2fd69d741a03607aae2137ceb98d20a9850efce9b"},"schema_version":"1.0","source":{"id":"2411.14085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14085","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14085v1","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14085","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"NJ524Y4J6N53","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"NJ524Y4J6N53772Z","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"NJ524Y4J","created_at":"2026-07-05T09:38:41Z"}],"graph_snapshots":[{"event_id":"sha256:2f6b76cf53eacc0311fc13fbd3a430628ab4f07ede428efe658206e34863faa0","target":"graph","created_at":"2026-07-05T09:38:41Z","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/2411.14085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to explore efficiently and effectively is a central challenge of reinforcement learning. In this work, we consider exploration through the lens of information theory. Specifically, we cast exploration as a problem of maximizing the Shannon entropy of the state occupation measure. This is done by maximizing a sequence of divergences between distributions representing an agent's past behavior and its current behavior. Intuitively, this encourages the agent to explore new behaviors that are distinct from past behaviors. Hence, we call our method RAMP, for ``$\\textbf{R}$unning $\\textbf","authors_text":"Dennis G. Wilson, Emmanuel Rachelson, Florent Teichteil-Koenigsbuch, Paul-Antoine Le Tolguenec, Yann Besse","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T12:51:09Z","title":"Exploration by Running Away from the Past"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14085","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":"sha256:38a64e00419302f842360ecfe5b2f20c8476451f6e32924632c7ba5cd5f4889c","target":"record","created_at":"2026-07-05T09:38:41Z","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":"aff435edcb603373034fad6392f3824d2a3a63ba5078391a35d33466ec963838","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T12:51:09Z","title_canon_sha256":"f1b046c1c0c84cd57a579fb2fd69d741a03607aae2137ceb98d20a9850efce9b"},"schema_version":"1.0","source":{"id":"2411.14085","kind":"arxiv","version":1}},"canonical_sha256":"6a7bae6389f37bbfff59d448b86768d3a87e7c5a9dfa2e0da4941c0251431f02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a7bae6389f37bbfff59d448b86768d3a87e7c5a9dfa2e0da4941c0251431f02","first_computed_at":"2026-07-05T09:38:41.462538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:41.462538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9rI1Fa8zGvXQ9vU2kRFp+OiSXzE7tAuyJvNpWTaXMxyq1g/Gph/XpPbj2Y7+8NpEdly3hZAnt9sRYzHjmsVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:41.462949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38a64e00419302f842360ecfe5b2f20c8476451f6e32924632c7ba5cd5f4889c","sha256:2f6b76cf53eacc0311fc13fbd3a430628ab4f07ede428efe658206e34863faa0"],"state_sha256":"f58e6d9021db0e709d77c30c678c29d1ab0d3fe7b645999679b7b83d9e77ad0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TI/ggS4e8/Vqca8LgPgoxCApXBzBoyUxaKwXnSxsdZ/f5BdK734CUosG4FKKAbyOLptQcYh3QeFC7mZZVMBFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:17:52.487586Z","bundle_sha256":"f3932cc3eb6c9b71b58af7a680a2b82c08fc57d2fb564c8d72355f6ca851713c"}}