{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N4XJB4LJ2JWHBWB5FQCH5SCMY3","short_pith_number":"pith:N4XJB4LJ","canonical_record":{"source":{"id":"2010.04646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T15:42:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c7beaa33b15dce8d3cca642993076f8b95c4ef0ed33b86c5810e8dffcf4d8b1","abstract_canon_sha256":"83a670b421506f1c39e4daf75a4cb35cb2bef66700d7cb25627cc1698a54fa4d"},"schema_version":"1.0"},"canonical_sha256":"6f2e90f169d26c70d83d2c047ec84cc6d664a55e222e512f56fdfd7c86cd994f","source":{"kind":"arxiv","id":"2010.04646","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N4XJB4LJ2JWHBWB5FQCH5SCMY3","target":"record","payload":{"canonical_record":{"source":{"id":"2010.04646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T15:42:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c7beaa33b15dce8d3cca642993076f8b95c4ef0ed33b86c5810e8dffcf4d8b1","abstract_canon_sha256":"83a670b421506f1c39e4daf75a4cb35cb2bef66700d7cb25627cc1698a54fa4d"},"schema_version":"1.0"},"canonical_sha256":"6f2e90f169d26c70d83d2c047ec84cc6d664a55e222e512f56fdfd7c86cd994f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:44.241451Z","signature_b64":"zxcyLNtIVhLLaV3KuO/MEX052pKdoIDEvO5WVgmZZHwuTFgqeDnb8aWqfZUh87vwDEnNqQEk92EC7mY04Y/WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f2e90f169d26c70d83d2c047ec84cc6d664a55e222e512f56fdfd7c86cd994f","last_reissued_at":"2026-07-05T11:03:44.240946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:44.240946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.04646","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":"2026-07-05T11:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJD4igLkU/NyCYeqk7PXx7lZKA5KDvnApUvPVoONVVF2bD+lc8DNvujF/DKe3EUlLC7cJ1ohrq19lPHyYviPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:02:21.152768Z"},"content_sha256":"35c05b4ae591edc1ed45c387d8480fa95a179f70111457fb2490edc7bcd53138","schema_version":"1.0","event_id":"sha256:35c05b4ae591edc1ed45c387d8480fa95a179f70111457fb2490edc7bcd53138"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N4XJB4LJ2JWHBWB5FQCH5SCMY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep RL With Information Constrained Policies: Generalization in Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris R. Sims, Gerald Tesauro, Matthew Riemer, Miao Liu, Tailia Malloy, Tim Klinger","submitted_at":"2020-10-09T15:42:21Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04646","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/2010.04646/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":"2026-07-05T11:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IpzySX/oR1csW6IMQDdx/zVdTEf6/1y6qvOslJr6lIIIgQTc9pjFVA+0PtdWQTaENEW7RECPMSmPQLo+2jICDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:02:21.154616Z"},"content_sha256":"e43cdb760187943ed093a5b5be5b6a948ca293c12a48d3550427d8359dc9c6bc","schema_version":"1.0","event_id":"sha256:e43cdb760187943ed093a5b5be5b6a948ca293c12a48d3550427d8359dc9c6bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/bundle.json","state_url":"https://pith.science/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/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":"2026-08-12T19:02:21Z","links":{"resolver":"https://pith.science/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3","bundle":"https://pith.science/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/bundle.json","state":"https://pith.science/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4XJB4LJ2JWHBWB5FQCH5SCMY3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSH2BkY55IdD2lCte8omVv1YiK1u0zxqcIhSz+h3y6vymAp3mjWQsSK8ktnT1+/16kd6vMAvnqVei6iuUau2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:02:21.161308Z","bundle_sha256":"190ed3297a1c88b53db3ca2f8d19e71c5e8eb20d2d2f21722d0a55a8b0eb270c"}}