{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3SKMMODOWHF3TIWPZGX7Q6S4K2","short_pith_number":"pith:3SKMMODO","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"},"canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","source":{"kind":"arxiv","id":"2006.04331","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04331","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04331v2","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04331","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"3SKMMODOWHF3","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"3SKMMODOWHF3TIWP","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"3SKMMODO","created_at":"2026-07-05T01:51:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3SKMMODOWHF3TIWPZGX7Q6S4K2","target":"record","payload":{"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"},"canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","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"},"source_kind":"arxiv","source_id":"2006.04331","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":"2026-07-05T01:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRbHmINMEysm7pnm9EY4WIeSFZvfVjl24kztrRmzql5Bi9daa0rtX1jWozpVjDKFgd1RpVY+vN7/QdAenfmkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:05:59.634452Z"},"content_sha256":"8afca109f910f0a1f21546c7356fa5fea8cdf419bf32527b40d338d895cb9ee4","schema_version":"1.0","event_id":"sha256:8afca109f910f0a1f21546c7356fa5fea8cdf419bf32527b40d338d895cb9ee4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3SKMMODOWHF3TIWPZGX7Q6S4K2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uMP8iqxjr9TJB6/0IWP9d25OX+qNmYSyHN/uP0m42nR14nps2muQ40a94lAB5vwK5Lw5ZWmmahZec98KL/7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:05:59.635104Z"},"content_sha256":"1195e5fb809107c4961730f86c9a7bb81f8c5c0ea76348c6be6f8c11ada90d74","schema_version":"1.0","event_id":"sha256:1195e5fb809107c4961730f86c9a7bb81f8c5c0ea76348c6be6f8c11ada90d74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/bundle.json","state_url":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/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":"2026-08-12T18:05:59Z","links":{"resolver":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2","bundle":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/bundle.json","state":"https://pith.science/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SKMMODOWHF3TIWPZGX7Q6S4K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3SKMMODOWHF3TIWPZGX7Q6S4K2","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":"a16845ff323435b228221536a1b284d74ecdea1b87cdc982e7552b5c3bc1194c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T02:49:47Z","title_canon_sha256":"9f13282f757b0d6ba3a7a2a27b73cbfcff1123b61b7b973965ec459b26e79cab"},"schema_version":"1.0","source":{"id":"2006.04331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04331","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04331v2","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04331","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"3SKMMODOWHF3","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"3SKMMODOWHF3TIWP","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"3SKMMODO","created_at":"2026-07-05T01:51:42Z"}],"graph_snapshots":[{"event_id":"sha256:1195e5fb809107c4961730f86c9a7bb81f8c5c0ea76348c6be6f8c11ada90d74","target":"graph","created_at":"2026-07-05T01:51:42Z","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/2006.04331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hiteshi Sharma, Rahul Jain","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T02:49:47Z","title":"Randomized Policy Learning for Continuous State and Action MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04331","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":"sha256:8afca109f910f0a1f21546c7356fa5fea8cdf419bf32527b40d338d895cb9ee4","target":"record","created_at":"2026-07-05T01:51:42Z","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":"a16845ff323435b228221536a1b284d74ecdea1b87cdc982e7552b5c3bc1194c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T02:49:47Z","title_canon_sha256":"9f13282f757b0d6ba3a7a2a27b73cbfcff1123b61b7b973965ec459b26e79cab"},"schema_version":"1.0","source":{"id":"2006.04331","kind":"arxiv","version":2}},"canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc94c6386eb1cbb9a2cfc9aff87a5c568a6d3305423a755bca7a69a3500a31b2","first_computed_at":"2026-07-05T01:51:42.211363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:42.211363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TZAU+3zKXaQa3wZ8vXS3j0bHWX43KaeAAy/RNT7RHTtVKZ0BsGX0gJ1WqRO3eRp96NyhWRXMNzhdxT/LpwWTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:42.211788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.04331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8afca109f910f0a1f21546c7356fa5fea8cdf419bf32527b40d338d895cb9ee4","sha256:1195e5fb809107c4961730f86c9a7bb81f8c5c0ea76348c6be6f8c11ada90d74"],"state_sha256":"434a63ff16803ad4ee04ac5c809b04a19b1abbb89a6b99d54d97f1fa4e27484e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJhg/v66/9ruA+W7rdoBhjUoP1iL+aJI9YgXt0EGMbSmlqGsR4jJJIv7acrmQxwovEFn9If5phPRr3JgjKJVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:05:59.639865Z","bundle_sha256":"9d685c9a7cac09cae9fe0018869cf579d92e7a2f11eb0c2de00458e4aa90ac79"}}