{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UYKWT4ZN362DBP4LUW3UDF5MWP","short_pith_number":"pith:UYKWT4ZN","schema_version":"1.0","canonical_sha256":"a61569f32ddfb430bf8ba5b74197acb3cca6c2840b58e666123b75258c7eb0f8","source":{"kind":"arxiv","id":"2208.00156","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement learning with experience replay and adaptation of action dispersion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mateusz Ostaszewski, Pawe{\\l} Wawrzy\\'nski, Wojciech Masarczyk","submitted_at":"2022-07-30T07:44:05Z","abstract_excerpt":"Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the current environment state. Existing methods that designate the action distribution dispersion require problem-dependent hyperparameters. In this paper, we propose to automatically designate the action distribution dispersion using the following principle: This distribution should have sufficient dispersion to enable the evaluation of future policies. To that end,"},"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":"2208.00156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-30T07:44:05Z","cross_cats_sorted":[],"title_canon_sha256":"f4b99e6560269c4efcda8e10b7ea759492eea00fe1bd32cd65b787c5ecb029cc","abstract_canon_sha256":"38c7b79577de4414951e0efd94b6c4ea772ca55c3a0a3693ce2254c90cf6cccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:48.331521Z","signature_b64":"+CvZsf3qXke9HDNSWu8Jvc2YCzFJs+AyMinAwZ2z/VCPg2ZNWVcRCoaVoYQxC4nMvjpBCusgFEVB5DPXYtkDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61569f32ddfb430bf8ba5b74197acb3cca6c2840b58e666123b75258c7eb0f8","last_reissued_at":"2026-07-05T04:44:48.331068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:48.331068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement learning with experience replay and adaptation of action dispersion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mateusz Ostaszewski, Pawe{\\l} Wawrzy\\'nski, Wojciech Masarczyk","submitted_at":"2022-07-30T07:44:05Z","abstract_excerpt":"Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the current environment state. Existing methods that designate the action distribution dispersion require problem-dependent hyperparameters. In this paper, we propose to automatically designate the action distribution dispersion using the following principle: This distribution should have sufficient dispersion to enable the evaluation of future policies. To that end,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00156","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/2208.00156/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":"2208.00156","created_at":"2026-07-05T04:44:48.331138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00156v1","created_at":"2026-07-05T04:44:48.331138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00156","created_at":"2026-07-05T04:44:48.331138+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYKWT4ZN362D","created_at":"2026-07-05T04:44:48.331138+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYKWT4ZN362DBP4L","created_at":"2026-07-05T04:44:48.331138+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYKWT4ZN","created_at":"2026-07-05T04:44:48.331138+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/UYKWT4ZN362DBP4LUW3UDF5MWP","json":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP.json","graph_json":"https://pith.science/api/pith-number/UYKWT4ZN362DBP4LUW3UDF5MWP/graph.json","events_json":"https://pith.science/api/pith-number/UYKWT4ZN362DBP4LUW3UDF5MWP/events.json","paper":"https://pith.science/paper/UYKWT4ZN"},"agent_actions":{"view_html":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP","download_json":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP.json","view_paper":"https://pith.science/paper/UYKWT4ZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00156&json=true","fetch_graph":"https://pith.science/api/pith-number/UYKWT4ZN362DBP4LUW3UDF5MWP/graph.json","fetch_events":"https://pith.science/api/pith-number/UYKWT4ZN362DBP4LUW3UDF5MWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP/action/storage_attestation","attest_author":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP/action/author_attestation","sign_citation":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP/action/citation_signature","submit_replication":"https://pith.science/pith/UYKWT4ZN362DBP4LUW3UDF5MWP/action/replication_record"}},"created_at":"2026-07-05T04:44:48.331138+00:00","updated_at":"2026-07-05T04:44:48.331138+00:00"}