{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AVTMULXARLP7QWKXP6XFP7LXTG","short_pith_number":"pith:AVTMULXA","canonical_record":{"source":{"id":"2305.05666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T17:59:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1defff114be1960b64901c297b78c91a490bc68448afdb12e561493799f4d117","abstract_canon_sha256":"6c6075747b8ae5ff5332fbb133c5928e0c61f4abba52a0483c6bd58a271c7fe0"},"schema_version":"1.0"},"canonical_sha256":"0566ca2ee08adff859577fae57fd7799a52bcb1c54ab3d84c14e9832b4baf19b","source":{"kind":"arxiv","id":"2305.05666","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05666","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05666v2","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05666","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"AVTMULXARLP7","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"AVTMULXARLP7QWKX","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"AVTMULXA","created_at":"2026-07-05T07:53:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AVTMULXARLP7QWKXP6XFP7LXTG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T17:59:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1defff114be1960b64901c297b78c91a490bc68448afdb12e561493799f4d117","abstract_canon_sha256":"6c6075747b8ae5ff5332fbb133c5928e0c61f4abba52a0483c6bd58a271c7fe0"},"schema_version":"1.0"},"canonical_sha256":"0566ca2ee08adff859577fae57fd7799a52bcb1c54ab3d84c14e9832b4baf19b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:08.293006Z","signature_b64":"9ldn5fXxBjTnEJdEXkPWMD2BpWz/jp6lH91orIWb9HhxY26sK5MhAeYUuD0HFG0/eGVAFFeGCiTwf8rLmFu2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0566ca2ee08adff859577fae57fd7799a52bcb1c54ab3d84c14e9832b4baf19b","last_reissued_at":"2026-07-05T07:53:08.292469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:08.292469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05666","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BvWa21VY5bS62seHmL5HmIDxEa8JeOnGREBDX8wZNIcKlpjB64akjPPBDlmfWAiRvxoNGBQ/BtvM5XAvEnVhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:52.233360Z"},"content_sha256":"d893d084070b2d6360c688da65a1c04576f6fd8b5748c68444499cd9923aceee","schema_version":"1.0","event_id":"sha256:d893d084070b2d6360c688da65a1c04576f6fd8b5748c68444499cd9923aceee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AVTMULXARLP7QWKXP6XFP7LXTG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Prakash Panangaden, Rosie Zhao, Sahand Rezaei-Shoshtari","submitted_at":"2023-05-09T17:59:10Z","abstract_excerpt":"Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In this paper, we study abstraction in the continuous-control setting, and extend the definition of Markov decision process (MDP) homomorphisms to the setting of continuous state and action spaces. We derive a policy gradient theorem on the abstract MDP for both stochastic and deterministic policies. Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization. Based on these theorems, we propose a family of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05666","kind":"arxiv","version":2},"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/2305.05666/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":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmW5ZYcXZ2t4AOm/X7ESNT8Hnriw/zTIZwfyhoi1QV2W7/Kq+kJKwd6zuhShuWv/mb9jKvPFn6Ispg4Ln4P+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:52.233743Z"},"content_sha256":"c0c9ec896ce4ddbbbf959d3a056dc70a54ad8a367a9bede5e88e1d99b6a505d0","schema_version":"1.0","event_id":"sha256:c0c9ec896ce4ddbbbf959d3a056dc70a54ad8a367a9bede5e88e1d99b6a505d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVTMULXARLP7QWKXP6XFP7LXTG/bundle.json","state_url":"https://pith.science/pith/AVTMULXARLP7QWKXP6XFP7LXTG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVTMULXARLP7QWKXP6XFP7LXTG/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":"2026-07-08T23:54:52Z","links":{"resolver":"https://pith.science/pith/AVTMULXARLP7QWKXP6XFP7LXTG","bundle":"https://pith.science/pith/AVTMULXARLP7QWKXP6XFP7LXTG/bundle.json","state":"https://pith.science/pith/AVTMULXARLP7QWKXP6XFP7LXTG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVTMULXARLP7QWKXP6XFP7LXTG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AVTMULXARLP7QWKXP6XFP7LXTG","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":"6c6075747b8ae5ff5332fbb133c5928e0c61f4abba52a0483c6bd58a271c7fe0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T17:59:10Z","title_canon_sha256":"1defff114be1960b64901c297b78c91a490bc68448afdb12e561493799f4d117"},"schema_version":"1.0","source":{"id":"2305.05666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05666","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05666v2","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05666","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"AVTMULXARLP7","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"AVTMULXARLP7QWKX","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"AVTMULXA","created_at":"2026-07-05T07:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:c0c9ec896ce4ddbbbf959d3a056dc70a54ad8a367a9bede5e88e1d99b6a505d0","target":"graph","created_at":"2026-07-05T07:53:08Z","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/2305.05666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In this paper, we study abstraction in the continuous-control setting, and extend the definition of Markov decision process (MDP) homomorphisms to the setting of continuous state and action spaces. We derive a policy gradient theorem on the abstract MDP for both stochastic and deterministic policies. Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization. Based on these theorems, we propose a family of","authors_text":"David Meger, Doina Precup, Prakash Panangaden, Rosie Zhao, Sahand Rezaei-Shoshtari","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T17:59:10Z","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05666","kind":"arxiv","version":2},"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:d893d084070b2d6360c688da65a1c04576f6fd8b5748c68444499cd9923aceee","target":"record","created_at":"2026-07-05T07:53:08Z","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":"6c6075747b8ae5ff5332fbb133c5928e0c61f4abba52a0483c6bd58a271c7fe0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T17:59:10Z","title_canon_sha256":"1defff114be1960b64901c297b78c91a490bc68448afdb12e561493799f4d117"},"schema_version":"1.0","source":{"id":"2305.05666","kind":"arxiv","version":2}},"canonical_sha256":"0566ca2ee08adff859577fae57fd7799a52bcb1c54ab3d84c14e9832b4baf19b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0566ca2ee08adff859577fae57fd7799a52bcb1c54ab3d84c14e9832b4baf19b","first_computed_at":"2026-07-05T07:53:08.292469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:08.292469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ldn5fXxBjTnEJdEXkPWMD2BpWz/jp6lH91orIWb9HhxY26sK5MhAeYUuD0HFG0/eGVAFFeGCiTwf8rLmFu2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:08.293006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d893d084070b2d6360c688da65a1c04576f6fd8b5748c68444499cd9923aceee","sha256:c0c9ec896ce4ddbbbf959d3a056dc70a54ad8a367a9bede5e88e1d99b6a505d0"],"state_sha256":"95fe921eab209c505ec952d623467d8bac36fc0f0042fdda188249650a130c36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9FBLlrFM+Nm3TyxxVTLvJpuApayNGKio+FtPrN7xjNg8Yz7Jc8ihVw25xpi5X6pEN1GBb4dTwIyq6TLrBfiTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:54:52.235952Z","bundle_sha256":"0eea58e5753ee178383547e2e2523610a99f3ad903621bcf4639ab50b67599b3"}}