{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R6H62XVW57UW33O7SEQVGJCYC4","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":"bdd456f76a711ae23eec018051b29e8629147a7ffde1f6561293752ffbc43477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T15:26:49Z","title_canon_sha256":"e6340929936b9d9f0d70196d04c8e3d9d28388e0b1deff12ad87adb114d7cb2e"},"schema_version":"1.0","source":{"id":"2209.07364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07364","created_at":"2026-07-05T04:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07364v1","created_at":"2026-07-05T04:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07364","created_at":"2026-07-05T04:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"R6H62XVW57UW","created_at":"2026-07-05T04:57:56Z"},{"alias_kind":"pith_short_16","alias_value":"R6H62XVW57UW33O7","created_at":"2026-07-05T04:57:56Z"},{"alias_kind":"pith_short_8","alias_value":"R6H62XVW","created_at":"2026-07-05T04:57:56Z"}],"graph_snapshots":[{"event_id":"sha256:52393c228604c79bc7d2b8b7df64c5741daee5f16ec1d2e2cfe534a5571ec216","target":"graph","created_at":"2026-07-05T04:57:56Z","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/2209.07364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuous-control setting. We extend the definition of MDP homomorphisms to encompass continuous actions in continuous state spaces. We derive a policy gradient theorem on the abstract MDP, which allows us to leverage approximate symmetries of the environment for policy optimization. Based on this theorem, we propose an actor-critic algorithm that is able to learn the policy and the MDP homomorphism map simultaneously, using","authors_text":"David Meger, Doina Precup, Prakash Panangaden, Rosie Zhao, Sahand Rezaei-Shoshtari","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T15:26:49Z","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07364","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":"sha256:92399a482291a99a026006cac871bd5a3bb5f00ffbf256852371e54656c3898c","target":"record","created_at":"2026-07-05T04:57:56Z","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":"bdd456f76a711ae23eec018051b29e8629147a7ffde1f6561293752ffbc43477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T15:26:49Z","title_canon_sha256":"e6340929936b9d9f0d70196d04c8e3d9d28388e0b1deff12ad87adb114d7cb2e"},"schema_version":"1.0","source":{"id":"2209.07364","kind":"arxiv","version":1}},"canonical_sha256":"8f8fed5eb6efe96deddf9121532458172d0536c62a54ceb4f4d519c90603218d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8fed5eb6efe96deddf9121532458172d0536c62a54ceb4f4d519c90603218d","first_computed_at":"2026-07-05T04:57:56.783541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:56.783541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6dyQbWTYe7A7siZC0in7W00QuWWC3mF1axSInSIqa14RbKmo/8ZbzdNONHP2qRx7mW0KCBtK4TO4dM61BuVkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:56.783945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92399a482291a99a026006cac871bd5a3bb5f00ffbf256852371e54656c3898c","sha256:52393c228604c79bc7d2b8b7df64c5741daee5f16ec1d2e2cfe534a5571ec216"],"state_sha256":"523b0ea13544a5816b295629fdc14a9b6aa2587bafc362e0cd71084ff9ca439e"}