{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N4XJB4LJ2JWHBWB5FQCH5SCMY3","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":"83a670b421506f1c39e4daf75a4cb35cb2bef66700d7cb25627cc1698a54fa4d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T15:42:21Z","title_canon_sha256":"4c7beaa33b15dce8d3cca642993076f8b95c4ef0ed33b86c5810e8dffcf4d8b1"},"schema_version":"1.0","source":{"id":"2010.04646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04646","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04646v1","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04646","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"N4XJB4LJ2JWH","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"N4XJB4LJ2JWHBWB5","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"N4XJB4LJ","created_at":"2026-07-05T11:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:e43cdb760187943ed093a5b5be5b6a948ca293c12a48d3550427d8359dc9c6bc","target":"graph","created_at":"2026-07-05T11:03:44Z","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/2010.04646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents. In this paper we explore the potential learning advantages a natural constraint on information flow might confer onto artificial agents in continuous control tasks. We focus on the model-free reinforcement learning (RL) setting and formalize our approach in terms of an information-theoretic constraint on the complexity of learned policies. We show that our ","authors_text":"Chris R. Sims, Gerald Tesauro, Matthew Riemer, Miao Liu, Tailia Malloy, Tim Klinger","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T15:42:21Z","title":"Deep RL With Information Constrained Policies: Generalization in Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04646","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":"sha256:35c05b4ae591edc1ed45c387d8480fa95a179f70111457fb2490edc7bcd53138","target":"record","created_at":"2026-07-05T11:03:44Z","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":"83a670b421506f1c39e4daf75a4cb35cb2bef66700d7cb25627cc1698a54fa4d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T15:42:21Z","title_canon_sha256":"4c7beaa33b15dce8d3cca642993076f8b95c4ef0ed33b86c5810e8dffcf4d8b1"},"schema_version":"1.0","source":{"id":"2010.04646","kind":"arxiv","version":1}},"canonical_sha256":"6f2e90f169d26c70d83d2c047ec84cc6d664a55e222e512f56fdfd7c86cd994f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f2e90f169d26c70d83d2c047ec84cc6d664a55e222e512f56fdfd7c86cd994f","first_computed_at":"2026-07-05T11:03:44.240946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:44.240946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zxcyLNtIVhLLaV3KuO/MEX052pKdoIDEvO5WVgmZZHwuTFgqeDnb8aWqfZUh87vwDEnNqQEk92EC7mY04Y/WDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:44.241451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35c05b4ae591edc1ed45c387d8480fa95a179f70111457fb2490edc7bcd53138","sha256:e43cdb760187943ed093a5b5be5b6a948ca293c12a48d3550427d8359dc9c6bc"],"state_sha256":"6315ae94ce2b946a79658bfe5b66adb2ca7da76b547af759b730c92c9e70e3bf"}