{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MB5P5RAJG3XHYL5WHQL36KZ5UY","short_pith_number":"pith:MB5P5RAJ","canonical_record":{"source":{"id":"2011.01859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-03T17:27:53Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"fc34e5d86e9bd38233fc7a5ec657274cbac90d4e38c53e901d66915cd6813121","abstract_canon_sha256":"df16dc64e4b3088b7288ebdc4dce11fe683bb3517478440c999cd495a59bc8a8"},"schema_version":"1.0"},"canonical_sha256":"607afec40936ee7c2fb63c17bf2b3da606be29f22aa0c434f0c11fd926f23481","source":{"kind":"arxiv","id":"2011.01859","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01859","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01859v1","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01859","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"MB5P5RAJG3XH","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"MB5P5RAJG3XHYL5W","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"MB5P5RAJ","created_at":"2026-07-05T01:48:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MB5P5RAJG3XHYL5WHQL36KZ5UY","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-03T17:27:53Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"fc34e5d86e9bd38233fc7a5ec657274cbac90d4e38c53e901d66915cd6813121","abstract_canon_sha256":"df16dc64e4b3088b7288ebdc4dce11fe683bb3517478440c999cd495a59bc8a8"},"schema_version":"1.0"},"canonical_sha256":"607afec40936ee7c2fb63c17bf2b3da606be29f22aa0c434f0c11fd926f23481","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:36.599264Z","signature_b64":"5Gyqso1KhEzllKgaQFwCUWVnN0G2DFHZG8fGV6hMB6abEvxH3dRrtLnNdMhkTPRddexcgpRKGHffnGr+GpjKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607afec40936ee7c2fb63c17bf2b3da606be29f22aa0c434f0c11fd926f23481","last_reissued_at":"2026-07-05T01:48:36.598766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:36.598766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01859","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":"2026-07-05T01:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ftlpi/9X/Xg4NaJMkglwQtOy9xTPyzXs8e6WKVgWZAvNKr3XJuAl8YKSsaKrQh2/0o2lRKKZ7Xbyc2J22dyfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:06:53.897069Z"},"content_sha256":"60e45fe4049f79c660dc6c231e662b33c8bb00f5649608703e6301bf109cc4f0","schema_version":"1.0","event_id":"sha256:60e45fe4049f79c660dc6c231e662b33c8bb00f5649608703e6301bf109cc4f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MB5P5RAJG3XHYL5WHQL36KZ5UY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Study of Policy Gradient on a Class of Exactly Solvable Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Anna Brandenberger, Colin Daniels, Doina Precup, Gavin McCracken, Prakash Panangaden, Rosie Zhao","submitted_at":"2020-11-03T17:27:53Z","abstract_excerpt":"Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a continuous-state Markov chain, whose transition probabilities are determined by the gradient of the distribution of the policy's value. Our approach relies heavily on random walk theory, specifically on affine Weyl groups. We construct a class of novel partially observable environments with controllable exploration difficulty, in which the value distribution, and hence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01859","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/2011.01859/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":"2026-07-05T01:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SAmdo1ySQQOR37IeysA532gsWoBiAifsp/CmipgOeygO+E77RcFT86apqwa0p1WK3AIYIlzNHjO2FfPF3duIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:06:53.897922Z"},"content_sha256":"ecea61f7647cfead6d26bc93dd78f3700b093adb00c4c437d950d856bd9a7deb","schema_version":"1.0","event_id":"sha256:ecea61f7647cfead6d26bc93dd78f3700b093adb00c4c437d950d856bd9a7deb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/bundle.json","state_url":"https://pith.science/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/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":"2026-08-04T17:06:53Z","links":{"resolver":"https://pith.science/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY","bundle":"https://pith.science/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/bundle.json","state":"https://pith.science/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MB5P5RAJG3XHYL5WHQL36KZ5UY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MB5P5RAJG3XHYL5WHQL36KZ5UY","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":"df16dc64e4b3088b7288ebdc4dce11fe683bb3517478440c999cd495a59bc8a8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-03T17:27:53Z","title_canon_sha256":"fc34e5d86e9bd38233fc7a5ec657274cbac90d4e38c53e901d66915cd6813121"},"schema_version":"1.0","source":{"id":"2011.01859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01859","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01859v1","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01859","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"MB5P5RAJG3XH","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"MB5P5RAJG3XHYL5W","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"MB5P5RAJ","created_at":"2026-07-05T01:48:36Z"}],"graph_snapshots":[{"event_id":"sha256:ecea61f7647cfead6d26bc93dd78f3700b093adb00c4c437d950d856bd9a7deb","target":"graph","created_at":"2026-07-05T01:48:36Z","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/2011.01859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a continuous-state Markov chain, whose transition probabilities are determined by the gradient of the distribution of the policy's value. Our approach relies heavily on random walk theory, specifically on affine Weyl groups. We construct a class of novel partially observable environments with controllable exploration difficulty, in which the value distribution, and hence ","authors_text":"Anna Brandenberger, Colin Daniels, Doina Precup, Gavin McCracken, Prakash Panangaden, Rosie Zhao","cross_cats":["math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-03T17:27:53Z","title":"A Study of Policy Gradient on a Class of Exactly Solvable Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01859","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":"sha256:60e45fe4049f79c660dc6c231e662b33c8bb00f5649608703e6301bf109cc4f0","target":"record","created_at":"2026-07-05T01:48:36Z","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":"df16dc64e4b3088b7288ebdc4dce11fe683bb3517478440c999cd495a59bc8a8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-03T17:27:53Z","title_canon_sha256":"fc34e5d86e9bd38233fc7a5ec657274cbac90d4e38c53e901d66915cd6813121"},"schema_version":"1.0","source":{"id":"2011.01859","kind":"arxiv","version":1}},"canonical_sha256":"607afec40936ee7c2fb63c17bf2b3da606be29f22aa0c434f0c11fd926f23481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"607afec40936ee7c2fb63c17bf2b3da606be29f22aa0c434f0c11fd926f23481","first_computed_at":"2026-07-05T01:48:36.598766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:36.598766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Gyqso1KhEzllKgaQFwCUWVnN0G2DFHZG8fGV6hMB6abEvxH3dRrtLnNdMhkTPRddexcgpRKGHffnGr+GpjKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:36.599264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60e45fe4049f79c660dc6c231e662b33c8bb00f5649608703e6301bf109cc4f0","sha256:ecea61f7647cfead6d26bc93dd78f3700b093adb00c4c437d950d856bd9a7deb"],"state_sha256":"5c6fdc6acd4c5ed8249cbfb0e7ee63f3cde44e8d848d5c9da68634a3d055c6ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aD7sgO9Ti8HxiFmPSvWuX7d4c/VbpBQbl4meS2zwz9wbf7Ziz4opUvuNTgTPVWmOxD8sOInLxe9EciKPL1VIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:06:53.903344Z","bundle_sha256":"929c7b9bb0e562ab966456114de0fc1d4dc5ca52650790c7cc41f2ffa3d30b8c"}}