{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3SU4LERB5WQUYU5JDBMGNNA6LR","short_pith_number":"pith:3SU4LERB","schema_version":"1.0","canonical_sha256":"dca9c59221eda14c53a9185866b41e5c496f77a5642371cbb7fa3f8e93706d35","source":{"kind":"arxiv","id":"2308.15911","version":1},"attestation_state":"computed","paper":{"title":"Cyclophobic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jan Robine, Peter Arndt, Stefan Harmeling, Stefan Sylvius Wagner","submitted_at":"2023-08-30T09:38:44Z","abstract_excerpt":"In environments with sparse rewards, finding a good inductive bias for exploration is crucial to the agent's success. However, there are two competing goals: novelty search and systematic exploration. While existing approaches such as curiosity-driven exploration find novelty, they sometimes do not systematically explore the whole state space, akin to depth-first-search vs breadth-first-search. In this paper, we propose a new intrinsic reward that is cyclophobic, i.e., it does not reward novelty, but punishes redundancy by avoiding cycles. Augmenting the cyclophobic intrinsic reward with a seq"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.15911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-30T09:38:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b1158cc35c87e79dca9caa68cb4849ec0436c49a09d354821d0dd5f94a0fcb6c","abstract_canon_sha256":"b6244e44d41cdad4faf058b284d4034cb1b2476520ca86cfa11addc87ddbbb89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:15.281060Z","signature_b64":"R0m92woQLtutouYxRi5IdnniQNQig8nxBY08CH4fKER8+boiXyPUyja3dpXSK09vjNzv7RM42plMpJsinSIzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dca9c59221eda14c53a9185866b41e5c496f77a5642371cbb7fa3f8e93706d35","last_reissued_at":"2026-07-05T06:46:15.280517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:15.280517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cyclophobic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jan Robine, Peter Arndt, Stefan Harmeling, Stefan Sylvius Wagner","submitted_at":"2023-08-30T09:38:44Z","abstract_excerpt":"In environments with sparse rewards, finding a good inductive bias for exploration is crucial to the agent's success. However, there are two competing goals: novelty search and systematic exploration. While existing approaches such as curiosity-driven exploration find novelty, they sometimes do not systematically explore the whole state space, akin to depth-first-search vs breadth-first-search. In this paper, we propose a new intrinsic reward that is cyclophobic, i.e., it does not reward novelty, but punishes redundancy by avoiding cycles. Augmenting the cyclophobic intrinsic reward with a seq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15911","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/2308.15911/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.15911","created_at":"2026-07-05T06:46:15.280574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15911v1","created_at":"2026-07-05T06:46:15.280574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15911","created_at":"2026-07-05T06:46:15.280574+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SU4LERB5WQU","created_at":"2026-07-05T06:46:15.280574+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SU4LERB5WQUYU5J","created_at":"2026-07-05T06:46:15.280574+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SU4LERB","created_at":"2026-07-05T06:46:15.280574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR","json":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR.json","graph_json":"https://pith.science/api/pith-number/3SU4LERB5WQUYU5JDBMGNNA6LR/graph.json","events_json":"https://pith.science/api/pith-number/3SU4LERB5WQUYU5JDBMGNNA6LR/events.json","paper":"https://pith.science/paper/3SU4LERB"},"agent_actions":{"view_html":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR","download_json":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR.json","view_paper":"https://pith.science/paper/3SU4LERB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15911&json=true","fetch_graph":"https://pith.science/api/pith-number/3SU4LERB5WQUYU5JDBMGNNA6LR/graph.json","fetch_events":"https://pith.science/api/pith-number/3SU4LERB5WQUYU5JDBMGNNA6LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR/action/storage_attestation","attest_author":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR/action/author_attestation","sign_citation":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR/action/citation_signature","submit_replication":"https://pith.science/pith/3SU4LERB5WQUYU5JDBMGNNA6LR/action/replication_record"}},"created_at":"2026-07-05T06:46:15.280574+00:00","updated_at":"2026-07-05T06:46:15.280574+00:00"}