{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZVWTJZ4XV5LYEHFOIL7DN4PC3","short_pith_number":"pith:SZVWTJZ4","schema_version":"1.0","canonical_sha256":"966b69a73cbd7abc10e57217f1b78f16efe3f5fab5a095e8f95003b29373a123","source":{"kind":"arxiv","id":"2510.13704","version":2},"attestation_state":"computed","paper":{"title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Johan Obando-Ceron, Pablo Samuel Castro, Samuel Lavoie, Scott Fujimoto, Walter Mayor","submitted_at":"2025-10-15T16:01:30Z","abstract_excerpt":"Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance. Noting that well-structured representations can improve the generalization and sample efficiency of deep reinforcement learning (RL) agents, we propose the use of simplicial embeddings: lightweight representation layers that constrain embeddings to simplicial structures. This geometric inductive bias results in spars"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.13704","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-15T16:01:30Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5e219f619de20a364a9a1a20cc38a5a4918ce2035ee029c8d876d43309751d2a","abstract_canon_sha256":"f4b73d67f1911a87d441aa45bbb11540c6ede54df12a593143b1830beca2ac1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:33.862245Z","signature_b64":"rt4bMLlzdAjcfDj4qwF23jslEVthZ7ZIfJY6Rclh9BLNlgzubDnHTNtxQWPGL8rBSPqCFk9x8RSq2MMmLVy7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966b69a73cbd7abc10e57217f1b78f16efe3f5fab5a095e8f95003b29373a123","last_reissued_at":"2026-06-04T01:08:33.861229Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:33.861229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Johan Obando-Ceron, Pablo Samuel Castro, Samuel Lavoie, Scott Fujimoto, Walter Mayor","submitted_at":"2025-10-15T16:01:30Z","abstract_excerpt":"Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance. Noting that well-structured representations can improve the generalization and sample efficiency of deep reinforcement learning (RL) agents, we propose the use of simplicial embeddings: lightweight representation layers that constrain embeddings to simplicial structures. This geometric inductive bias results in spars"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.13704","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/2510.13704/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.13704","created_at":"2026-06-04T01:08:33.861389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.13704v2","created_at":"2026-06-04T01:08:33.861389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.13704","created_at":"2026-06-04T01:08:33.861389+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZVWTJZ4XV5L","created_at":"2026-06-04T01:08:33.861389+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZVWTJZ4XV5LYEHF","created_at":"2026-06-04T01:08:33.861389+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZVWTJZ4","created_at":"2026-06-04T01:08:33.861389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12612","citing_title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3","json":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3.json","graph_json":"https://pith.science/api/pith-number/SZVWTJZ4XV5LYEHFOIL7DN4PC3/graph.json","events_json":"https://pith.science/api/pith-number/SZVWTJZ4XV5LYEHFOIL7DN4PC3/events.json","paper":"https://pith.science/paper/SZVWTJZ4"},"agent_actions":{"view_html":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3","download_json":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3.json","view_paper":"https://pith.science/paper/SZVWTJZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.13704&json=true","fetch_graph":"https://pith.science/api/pith-number/SZVWTJZ4XV5LYEHFOIL7DN4PC3/graph.json","fetch_events":"https://pith.science/api/pith-number/SZVWTJZ4XV5LYEHFOIL7DN4PC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3/action/storage_attestation","attest_author":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3/action/author_attestation","sign_citation":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3/action/citation_signature","submit_replication":"https://pith.science/pith/SZVWTJZ4XV5LYEHFOIL7DN4PC3/action/replication_record"}},"created_at":"2026-06-04T01:08:33.861389+00:00","updated_at":"2026-06-04T01:08:33.861389+00:00"}