{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3SKMMODOWHF3TIWPZGX7Q6S4K2","short_pith_number":"pith:3SKMMODO","schema_version":"1.0","canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","source":{"kind":"arxiv","id":"2006.04331","version":2},"attestation_state":"computed","paper":{"title":"Randomized Policy Learning for Continuous State and Action MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiteshi Sharma, Rahul Jain","submitted_at":"2020-06-08T02:49:47Z","abstract_excerpt":"Deep reinforcement learning methods have achieved state-of-the-art results in a variety of challenging, high-dimensional domains ranging from video games to locomotion. The key to success has been the use of deep neural networks used to approximate the policy and value function. Yet, substantial tuning of weights is required for good results. We instead use randomized function approximation. Such networks are not only cheaper than training fully connected networks but also improve the numerical performance. We present \\texttt{RANDPOL}, a generalized policy iteration algorithm for MDPs with con"},"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":"2006.04331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T02:49:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9f13282f757b0d6ba3a7a2a27b73cbfcff1123b61b7b973965ec459b26e79cab","abstract_canon_sha256":"a16845ff323435b228221536a1b284d74ecdea1b87cdc982e7552b5c3bc1194c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:42.211788Z","signature_b64":"TZAU+3zKXaQa3wZ8vXS3j0bHWX43KaeAAy/RNT7RHTtVKZ0BsGX0gJ1WqRO3eRp96NyhWRXMNzhdxT/LpwWTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","last_reissued_at":"2026-07-05T01:51:42.211363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:42.211363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Policy Learning for Continuous State and Action MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiteshi Sharma, Rahul Jain","submitted_at":"2020-06-08T02:49:47Z","abstract_excerpt":"Deep reinforcement learning methods have achieved state-of-the-art results in a variety of challenging, high-dimensional domains ranging from video games to locomotion. The key to success has been the use of deep neural networks used to approximate the policy and value function. Yet, substantial tuning of weights is required for good results. We instead use randomized function approximation. Such networks are not only cheaper than training fully connected networks but also improve the numerical performance. We present \\texttt{RANDPOL}, a generalized policy iteration algorithm for MDPs with con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04331","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/2006.04331/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":"2006.04331","created_at":"2026-07-05T01:51:42.211422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04331v2","created_at":"2026-07-05T01:51:42.211422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04331","created_at":"2026-07-05T01:51:42.211422+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SKMMODOWHF3","created_at":"2026-07-05T01:51:42.211422+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SKMMODOWHF3TIWP","created_at":"2026-07-05T01:51:42.211422+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SKMMODO","created_at":"2026-07-05T01:51:42.211422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2","json":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2.json","graph_json":"https://pith.science/api/pith-number/3SKMMODOWHF3TIWPZGX7Q6S4K2/graph.json","events_json":"https://pith.science/api/pith-number/3SKMMODOWHF3TIWPZGX7Q6S4K2/events.json","paper":"https://pith.science/paper/3SKMMODO"},"agent_actions":{"view_html":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2","download_json":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2.json","view_paper":"https://pith.science/paper/3SKMMODO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04331&json=true","fetch_graph":"https://pith.science/api/pith-number/3SKMMODOWHF3TIWPZGX7Q6S4K2/graph.json","fetch_events":"https://pith.science/api/pith-number/3SKMMODOWHF3TIWPZGX7Q6S4K2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/action/storage_attestation","attest_author":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/action/author_attestation","sign_citation":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/action/citation_signature","submit_replication":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/action/replication_record"}},"created_at":"2026-07-05T01:51:42.211422+00:00","updated_at":"2026-07-05T01:51:42.211422+00:00"}