{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UNZV4PFVBEBHZNRVPTUTREDNW3","short_pith_number":"pith:UNZV4PFV","canonical_record":{"source":{"id":"1901.10500","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30a1540ea84d69c34db0ca258eaf16f2306fcbaf06600b26a6fbe15e3c7a50b1","abstract_canon_sha256":"861a7699a6b6161a986d27280803c9ed548ba25f145a166a1df3981887e026e2"},"schema_version":"1.0"},"canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","source":{"kind":"arxiv","id":"1901.10500","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10500","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10500v4","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10500","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"UNZV4PFVBEBH","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"UNZV4PFVBEBHZNRV","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"UNZV4PFV","created_at":"2026-07-05T00:49:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UNZV4PFVBEBHZNRVPTUTREDNW3","target":"record","payload":{"canonical_record":{"source":{"id":"1901.10500","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30a1540ea84d69c34db0ca258eaf16f2306fcbaf06600b26a6fbe15e3c7a50b1","abstract_canon_sha256":"861a7699a6b6161a986d27280803c9ed548ba25f145a166a1df3981887e026e2"},"schema_version":"1.0"},"canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:22.996910Z","signature_b64":"jbDV+Ox3btTKo34xBVWy+FaqqE6gjcQCi/o2jv+ZIAKDdXYY+Oi0RXc1t7NJTWuFayjxN/ugkkzNAV1r9YHxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","last_reissued_at":"2026-07-05T00:49:22.996494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:22.996494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.10500","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2n/CD28xeAmFtCwG/tklDP6elIPYG0wz+RSdEfVkt/4svAd9xGh8OPAa4IMZhv05mWOBC0LUxLBGHWomblTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:21.237279Z"},"content_sha256":"6edc8efc55cc6c64674fd9236788b41a2ebb933bbbae55a57f24391b8c91ae00","schema_version":"1.0","event_id":"sha256:6edc8efc55cc6c64674fd9236788b41a2ebb933bbbae55a57f24391b8c91ae00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UNZV4PFVBEBHZNRVPTUTREDNW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discretizing Continuous Action Space for On-Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shipra Agrawal, Yunhao Tang","submitted_at":"2019-01-29T19:19:50Z","abstract_excerpt":"In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10500","kind":"arxiv","version":4},"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/1901.10500/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":"2026-07-05T00:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IgkJDVIgYEWRCDI5f9ZZgccDMSuYQXfcQpnji3WJlhSFFi5a7i2x+7Zn6+AtIvFwh/qBYdo8EvFl3PT/19aMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:21.237771Z"},"content_sha256":"4b7e1eada02b0c97e024f8a1c14528a63f8acdbd47f86d2a8125187194c2b518","schema_version":"1.0","event_id":"sha256:4b7e1eada02b0c97e024f8a1c14528a63f8acdbd47f86d2a8125187194c2b518"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/bundle.json","state_url":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/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":"2026-08-08T22:51:21Z","links":{"resolver":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3","bundle":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/bundle.json","state":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UNZV4PFVBEBHZNRVPTUTREDNW3","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":"861a7699a6b6161a986d27280803c9ed548ba25f145a166a1df3981887e026e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","title_canon_sha256":"30a1540ea84d69c34db0ca258eaf16f2306fcbaf06600b26a6fbe15e3c7a50b1"},"schema_version":"1.0","source":{"id":"1901.10500","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10500","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10500v4","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10500","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"UNZV4PFVBEBH","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"UNZV4PFVBEBHZNRV","created_at":"2026-07-05T00:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"UNZV4PFV","created_at":"2026-07-05T00:49:22Z"}],"graph_snapshots":[{"event_id":"sha256:4b7e1eada02b0c97e024f8a1c14528a63f8acdbd47f86d2a8125187194c2b518","target":"graph","created_at":"2026-07-05T00:49:22Z","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/1901.10500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductiv","authors_text":"Shipra Agrawal, Yunhao Tang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","title":"Discretizing Continuous Action Space for On-Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10500","kind":"arxiv","version":4},"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":"sha256:6edc8efc55cc6c64674fd9236788b41a2ebb933bbbae55a57f24391b8c91ae00","target":"record","created_at":"2026-07-05T00:49:22Z","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":"861a7699a6b6161a986d27280803c9ed548ba25f145a166a1df3981887e026e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","title_canon_sha256":"30a1540ea84d69c34db0ca258eaf16f2306fcbaf06600b26a6fbe15e3c7a50b1"},"schema_version":"1.0","source":{"id":"1901.10500","kind":"arxiv","version":4}},"canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","first_computed_at":"2026-07-05T00:49:22.996494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:22.996494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jbDV+Ox3btTKo34xBVWy+FaqqE6gjcQCi/o2jv+ZIAKDdXYY+Oi0RXc1t7NJTWuFayjxN/ugkkzNAV1r9YHxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:22.996910Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10500","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6edc8efc55cc6c64674fd9236788b41a2ebb933bbbae55a57f24391b8c91ae00","sha256:4b7e1eada02b0c97e024f8a1c14528a63f8acdbd47f86d2a8125187194c2b518"],"state_sha256":"75121e6e0a515ee98d254d91dbfe977a8420c29d421ee6d016e18ba31f54c133"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKztESs2p8U8McYePFD6SUvr+KorgodF4Zj3/LEjFGSDWCEKR8AMDSfdgRE/FVfXUDV+f5AH1X83s1hv5FaNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:51:21.242068Z","bundle_sha256":"835f52f77f8a4c063da3819e4885a0df0667c3edc4591b7e1673138a9fef70dd"}}