{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4H34HW4RHS2VYYS7D7AGBPTMFU","short_pith_number":"pith:4H34HW4R","canonical_record":{"source":{"id":"2409.08938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:56:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc1ad7d72946357cff5448e4065cd212558021902953a7e2f5db6f7c22650a85","abstract_canon_sha256":"5b29a3e02ff4ecd8aba898e8bf612986ef8553ec039f345158ed5b6110c17083"},"schema_version":"1.0"},"canonical_sha256":"e1f7c3db913cb55c625f1fc060be6c2d2b9724db3b9ae13c255ca95b2a6cd9a5","source":{"kind":"arxiv","id":"2409.08938","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08938","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08938v1","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08938","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"4H34HW4RHS2V","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"4H34HW4RHS2VYYS7","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"4H34HW4R","created_at":"2026-07-05T09:06:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4H34HW4RHS2VYYS7D7AGBPTMFU","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:56:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc1ad7d72946357cff5448e4065cd212558021902953a7e2f5db6f7c22650a85","abstract_canon_sha256":"5b29a3e02ff4ecd8aba898e8bf612986ef8553ec039f345158ed5b6110c17083"},"schema_version":"1.0"},"canonical_sha256":"e1f7c3db913cb55c625f1fc060be6c2d2b9724db3b9ae13c255ca95b2a6cd9a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:49.901110Z","signature_b64":"KNl8G0+tEQRf1TxLLjq1spJFCyEaAtxHOrDCSuanPzV77zDG5OQHM07lWrljqpP60+KIORK5YCtCcAkiFUFGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1f7c3db913cb55c625f1fc060be6c2d2b9724db3b9ae13c255ca95b2a6cd9a5","last_reissued_at":"2026-07-05T09:06:49.900625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:49.900625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08938","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":"2026-07-05T09:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ae5RlAsr0VcWSNPEfnyIGtyzpnn+vbBBkLccR4mLFvu8/G+44h07OYttqDGlAiaIq0aSKfu59D8txXOEHvuVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:10:35.397545Z"},"content_sha256":"f105a273f3888536ee92703084de95c03b56ff6aed3ec5f219497a5fc69e67f8","schema_version":"1.0","event_id":"sha256:f105a273f3888536ee92703084de95c03b56ff6aed3ec5f219497a5fc69e67f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4H34HW4RHS2VYYS7D7AGBPTMFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bumkyu Choi, Jean Seong Bjorn Choe, Jong-Kook Kim","submitted_at":"2024-09-13T15:56:26Z","abstract_excerpt":"This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08938","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/2409.08938/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":"2026-07-05T09:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"djUVBbx0nIiQVcqY6ygrIpPsnwx1IDIbz9lpB8h3aOIa6ZxrA8ZXb0qJuzh2l/l345uDjVaXG2CKheUChXR0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:10:35.398072Z"},"content_sha256":"4241bb39b2163b650f9b47f894cc0f6a387dc6314e0fe692183d3366b620044e","schema_version":"1.0","event_id":"sha256:4241bb39b2163b650f9b47f894cc0f6a387dc6314e0fe692183d3366b620044e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/bundle.json","state_url":"https://pith.science/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/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":"2026-08-19T04:10:35Z","links":{"resolver":"https://pith.science/pith/4H34HW4RHS2VYYS7D7AGBPTMFU","bundle":"https://pith.science/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/bundle.json","state":"https://pith.science/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4H34HW4RHS2VYYS7D7AGBPTMFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4H34HW4RHS2VYYS7D7AGBPTMFU","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":"5b29a3e02ff4ecd8aba898e8bf612986ef8553ec039f345158ed5b6110c17083","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:56:26Z","title_canon_sha256":"dc1ad7d72946357cff5448e4065cd212558021902953a7e2f5db6f7c22650a85"},"schema_version":"1.0","source":{"id":"2409.08938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08938","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08938v1","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08938","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"4H34HW4RHS2V","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"4H34HW4RHS2VYYS7","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"4H34HW4R","created_at":"2026-07-05T09:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:4241bb39b2163b650f9b47f894cc0f6a387dc6314e0fe692183d3366b620044e","target":"graph","created_at":"2026-07-05T09:06:49Z","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/2409.08938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or syst","authors_text":"Bumkyu Choi, Jean Seong Bjorn Choe, Jong-Kook Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:56:26Z","title":"Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08938","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:f105a273f3888536ee92703084de95c03b56ff6aed3ec5f219497a5fc69e67f8","target":"record","created_at":"2026-07-05T09:06:49Z","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":"5b29a3e02ff4ecd8aba898e8bf612986ef8553ec039f345158ed5b6110c17083","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:56:26Z","title_canon_sha256":"dc1ad7d72946357cff5448e4065cd212558021902953a7e2f5db6f7c22650a85"},"schema_version":"1.0","source":{"id":"2409.08938","kind":"arxiv","version":1}},"canonical_sha256":"e1f7c3db913cb55c625f1fc060be6c2d2b9724db3b9ae13c255ca95b2a6cd9a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1f7c3db913cb55c625f1fc060be6c2d2b9724db3b9ae13c255ca95b2a6cd9a5","first_computed_at":"2026-07-05T09:06:49.900625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:49.900625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KNl8G0+tEQRf1TxLLjq1spJFCyEaAtxHOrDCSuanPzV77zDG5OQHM07lWrljqpP60+KIORK5YCtCcAkiFUFGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:49.901110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f105a273f3888536ee92703084de95c03b56ff6aed3ec5f219497a5fc69e67f8","sha256:4241bb39b2163b650f9b47f894cc0f6a387dc6314e0fe692183d3366b620044e"],"state_sha256":"aaffb6cf8d29661b55eb17cfa5cb4f0a29fe5d6d5d22d3fbd54f26ca8a758459"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUbJkyAFqoCijfvDj7h0dNb9ZAD4Lcu3hOJK1TbKgMC64EVJuW5xXctgYoz/692AFvHhyUGBb+XaXVucKws9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:10:35.404202Z","bundle_sha256":"0fd78040e3c42171932837c5617c2f12644e0cca6f3b895c562d17e8d7634942"}}