{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C3WOTNAY7OFAZEW7747THJTVUB","short_pith_number":"pith:C3WOTNAY","canonical_record":{"source":{"id":"2408.00309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T06:06:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96db77bf025e04df40627b40f518e2bf144eef6537685f0a9436f0b746bd5e01","abstract_canon_sha256":"b2e69a7616940beb3abcd59d3410ae8024abe1e1e04a5ca08621979977c8f4ad"},"schema_version":"1.0"},"canonical_sha256":"16ece9b418fb8a0c92dfff3f33a675a05fa5fadcc62397e647c0de7589b89bd5","source":{"kind":"arxiv","id":"2408.00309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00309","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00309v1","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00309","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"C3WOTNAY7OFA","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"C3WOTNAY7OFAZEW7","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"C3WOTNAY","created_at":"2026-07-05T08:51:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C3WOTNAY7OFAZEW7747THJTVUB","target":"record","payload":{"canonical_record":{"source":{"id":"2408.00309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T06:06:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96db77bf025e04df40627b40f518e2bf144eef6537685f0a9436f0b746bd5e01","abstract_canon_sha256":"b2e69a7616940beb3abcd59d3410ae8024abe1e1e04a5ca08621979977c8f4ad"},"schema_version":"1.0"},"canonical_sha256":"16ece9b418fb8a0c92dfff3f33a675a05fa5fadcc62397e647c0de7589b89bd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:01.628862Z","signature_b64":"2hkw+efPI+JO2K2/snlm5zLGBO29PLy09Ybs8AP5Ykf9eDrci5aXHmXuz1UXuTVqjJjBoIDB7WiJQVXVL9fcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16ece9b418fb8a0c92dfff3f33a675a05fa5fadcc62397e647c0de7589b89bd5","last_reissued_at":"2026-07-05T08:51:01.628422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:01.628422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.00309","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":"2026-07-05T08:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glrfHsI/L4b+ayHgAy+KYtLHCeHdQ2qyKS7oExNWxaW5/YG1cmYPu9258WsI31XRRTpZpmLuhdBTK85u1wSBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:42:04.506436Z"},"content_sha256":"a0587f1d837f8be66a2f74b760ea64fafe1b467a36512f3a8a72decc559baad0","schema_version":"1.0","event_id":"sha256:a0587f1d837f8be66a2f74b760ea64fafe1b467a36512f3a8a72decc559baad0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C3WOTNAY7OFAZEW7747THJTVUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunlin Chen, Dongbin Zhao, Yuanheng Zhu, Yuanyang Zhu, Zhi Wang","submitted_at":"2024-08-01T06:06:53Z","abstract_excerpt":"For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the discrete atomic actions, the explosion in the number of discrete actions can possess undesired properties and induce a higher variance for the policy gradient estimator. In this paper, we introduce a straightforward architecture that addresses this issue by constraining the discrete policy to be unimodal using Poisson probability distributions. This unimodal architecture can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00309","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/2408.00309/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":"2026-07-05T08:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d7PDEsuKwAJ3YlBvDhDRYN6lhEmsKoSHcOlxtGKwlGTgPkQsUQZp7iR8RSC5pZzrUtGW/BnEHFEmPtTjmRRDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:42:04.509410Z"},"content_sha256":"71ab1d79287f546dcff0c42ade24b57423be63cba4c665a0149b87ff75d9c0eb","schema_version":"1.0","event_id":"sha256:71ab1d79287f546dcff0c42ade24b57423be63cba4c665a0149b87ff75d9c0eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C3WOTNAY7OFAZEW7747THJTVUB/bundle.json","state_url":"https://pith.science/pith/C3WOTNAY7OFAZEW7747THJTVUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C3WOTNAY7OFAZEW7747THJTVUB/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":"2026-07-31T23:42:04Z","links":{"resolver":"https://pith.science/pith/C3WOTNAY7OFAZEW7747THJTVUB","bundle":"https://pith.science/pith/C3WOTNAY7OFAZEW7747THJTVUB/bundle.json","state":"https://pith.science/pith/C3WOTNAY7OFAZEW7747THJTVUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C3WOTNAY7OFAZEW7747THJTVUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C3WOTNAY7OFAZEW7747THJTVUB","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":"b2e69a7616940beb3abcd59d3410ae8024abe1e1e04a5ca08621979977c8f4ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T06:06:53Z","title_canon_sha256":"96db77bf025e04df40627b40f518e2bf144eef6537685f0a9436f0b746bd5e01"},"schema_version":"1.0","source":{"id":"2408.00309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00309","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00309v1","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00309","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"C3WOTNAY7OFA","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"C3WOTNAY7OFAZEW7","created_at":"2026-07-05T08:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"C3WOTNAY","created_at":"2026-07-05T08:51:01Z"}],"graph_snapshots":[{"event_id":"sha256:71ab1d79287f546dcff0c42ade24b57423be63cba4c665a0149b87ff75d9c0eb","target":"graph","created_at":"2026-07-05T08:51:01Z","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/2408.00309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the discrete atomic actions, the explosion in the number of discrete actions can possess undesired properties and induce a higher variance for the policy gradient estimator. In this paper, we introduce a straightforward architecture that addresses this issue by constraining the discrete policy to be unimodal using Poisson probability distributions. This unimodal architecture can be","authors_text":"Chunlin Chen, Dongbin Zhao, Yuanheng Zhu, Yuanyang Zhu, Zhi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T06:06:53Z","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00309","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:a0587f1d837f8be66a2f74b760ea64fafe1b467a36512f3a8a72decc559baad0","target":"record","created_at":"2026-07-05T08:51:01Z","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":"b2e69a7616940beb3abcd59d3410ae8024abe1e1e04a5ca08621979977c8f4ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T06:06:53Z","title_canon_sha256":"96db77bf025e04df40627b40f518e2bf144eef6537685f0a9436f0b746bd5e01"},"schema_version":"1.0","source":{"id":"2408.00309","kind":"arxiv","version":1}},"canonical_sha256":"16ece9b418fb8a0c92dfff3f33a675a05fa5fadcc62397e647c0de7589b89bd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16ece9b418fb8a0c92dfff3f33a675a05fa5fadcc62397e647c0de7589b89bd5","first_computed_at":"2026-07-05T08:51:01.628422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:01.628422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hkw+efPI+JO2K2/snlm5zLGBO29PLy09Ybs8AP5Ykf9eDrci5aXHmXuz1UXuTVqjJjBoIDB7WiJQVXVL9fcDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:01.628862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0587f1d837f8be66a2f74b760ea64fafe1b467a36512f3a8a72decc559baad0","sha256:71ab1d79287f546dcff0c42ade24b57423be63cba4c665a0149b87ff75d9c0eb"],"state_sha256":"d318ec90646e72c4f6ad597ef8e64dbb2b4ebf1741257f39af75e8bcb1581eb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jO3RPTKqTVArTflZck5ispchshUiH1A5Z4LGDkLVUZdyrcDeOoWbDtXl8m8HfsnY76HKvYRrU5SGwN2yIbBGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:42:04.515472Z","bundle_sha256":"dfc19e8d742dce8c9c3684cd9fe7e7e5595ae11ee88e3a2a80ce6fd9f98c6edc"}}