{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O5CPUYIZBHKIDUNXBYJHAIIUPK","short_pith_number":"pith:O5CPUYIZ","canonical_record":{"source":{"id":"2001.02652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-08T17:50:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"055835c4dcfcf7f5f74bdfc33b6a12db38d1d501a47c85dda22ba2c523760cff","abstract_canon_sha256":"2ea915571328f982b4d67a10140e615b1473088dc17507ea3d9c09ca4992dd8a"},"schema_version":"1.0"},"canonical_sha256":"7744fa611909d481d1b70e127021147aa6ca2d963cc96cacc04e811e569d1ec3","source":{"kind":"arxiv","id":"2001.02652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.02652","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"arxiv_version","alias_value":"2001.02652v1","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.02652","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_12","alias_value":"O5CPUYIZBHKI","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"O5CPUYIZBHKIDUNX","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"O5CPUYIZ","created_at":"2026-07-05T00:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O5CPUYIZBHKIDUNXBYJHAIIUPK","target":"record","payload":{"canonical_record":{"source":{"id":"2001.02652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-08T17:50:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"055835c4dcfcf7f5f74bdfc33b6a12db38d1d501a47c85dda22ba2c523760cff","abstract_canon_sha256":"2ea915571328f982b4d67a10140e615b1473088dc17507ea3d9c09ca4992dd8a"},"schema_version":"1.0"},"canonical_sha256":"7744fa611909d481d1b70e127021147aa6ca2d963cc96cacc04e811e569d1ec3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:19.814468Z","signature_b64":"jeunq+KKMkWTIra2IWuDib4y1DNLZ+fVdONUNIUU/4/z212aFCGYq87mNl56R3GnSeGg6/sn8ouGvaJtEXw0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7744fa611909d481d1b70e127021147aa6ca2d963cc96cacc04e811e569d1ec3","last_reissued_at":"2026-07-05T00:32:19.813862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:19.813862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.02652","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":"2026-07-05T00:32:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ata+P45eN1SURBF/br8TwtVgcWBoo/1w1OlSlFwFazHVZUVET1ByuZrXi4g/LxAxq2/2XReaj944jVPw6BIyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:48.551075Z"},"content_sha256":"adc4d866647a66f493ba9fd8f988129a0c640a80786c41dd7a14a23ddab5c59a","schema_version":"1.0","event_id":"sha256:adc4d866647a66f493ba9fd8f988129a0c640a80786c41dd7a14a23ddab5c59a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O5CPUYIZBHKIDUNXBYJHAIIUPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-based Distributional Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Keuntaek Lee, Rahul Singh, Yongxin Chen","submitted_at":"2020-01-08T17:50:23Z","abstract_excerpt":"Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards. Most of the existing literature on DRL focuses on problems with discrete action space and value based methods. In this work, motivated by applications in robotics with continuous action space control settings, we propose sample-based distributional policy gradient (SDPG) algorithm. It models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.02652","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/2001.02652/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":"2026-07-05T00:32:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/nijKRmxW3j1bzE7l/5dQuB7c7Drc3LkJbqUr48syLW3FafjxkA2Nb6XFoaONpLPx10z8L6kzhvcEcJRfCdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:48.551466Z"},"content_sha256":"335855074f80d2f28417f1f08343e6186f02b94402f5260cb4f381286db30af6","schema_version":"1.0","event_id":"sha256:335855074f80d2f28417f1f08343e6186f02b94402f5260cb4f381286db30af6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/bundle.json","state_url":"https://pith.science/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/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":"2026-07-06T16:18:48Z","links":{"resolver":"https://pith.science/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK","bundle":"https://pith.science/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/bundle.json","state":"https://pith.science/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5CPUYIZBHKIDUNXBYJHAIIUPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O5CPUYIZBHKIDUNXBYJHAIIUPK","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":"2ea915571328f982b4d67a10140e615b1473088dc17507ea3d9c09ca4992dd8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-08T17:50:23Z","title_canon_sha256":"055835c4dcfcf7f5f74bdfc33b6a12db38d1d501a47c85dda22ba2c523760cff"},"schema_version":"1.0","source":{"id":"2001.02652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.02652","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"arxiv_version","alias_value":"2001.02652v1","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.02652","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_12","alias_value":"O5CPUYIZBHKI","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"O5CPUYIZBHKIDUNX","created_at":"2026-07-05T00:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"O5CPUYIZ","created_at":"2026-07-05T00:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:335855074f80d2f28417f1f08343e6186f02b94402f5260cb4f381286db30af6","target":"graph","created_at":"2026-07-05T00:32:19Z","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/2001.02652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards. Most of the existing literature on DRL focuses on problems with discrete action space and value based methods. In this work, motivated by applications in robotics with continuous action space control settings, we propose sample-based distributional policy gradient (SDPG) algorithm. It models ","authors_text":"Keuntaek Lee, Rahul Singh, Yongxin Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-08T17:50:23Z","title":"Sample-based Distributional Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.02652","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:adc4d866647a66f493ba9fd8f988129a0c640a80786c41dd7a14a23ddab5c59a","target":"record","created_at":"2026-07-05T00:32:19Z","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":"2ea915571328f982b4d67a10140e615b1473088dc17507ea3d9c09ca4992dd8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-08T17:50:23Z","title_canon_sha256":"055835c4dcfcf7f5f74bdfc33b6a12db38d1d501a47c85dda22ba2c523760cff"},"schema_version":"1.0","source":{"id":"2001.02652","kind":"arxiv","version":1}},"canonical_sha256":"7744fa611909d481d1b70e127021147aa6ca2d963cc96cacc04e811e569d1ec3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7744fa611909d481d1b70e127021147aa6ca2d963cc96cacc04e811e569d1ec3","first_computed_at":"2026-07-05T00:32:19.813862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:19.813862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeunq+KKMkWTIra2IWuDib4y1DNLZ+fVdONUNIUU/4/z212aFCGYq87mNl56R3GnSeGg6/sn8ouGvaJtEXw0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:19.814468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.02652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc4d866647a66f493ba9fd8f988129a0c640a80786c41dd7a14a23ddab5c59a","sha256:335855074f80d2f28417f1f08343e6186f02b94402f5260cb4f381286db30af6"],"state_sha256":"245c1aad1d7b3a76dda9b79b19505e822484f7fbbe5f69f92ce16d13356d94ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/MQCaDn1SyWCzGwydojxlWdyTm1KrG3GJiez/pivNOcZVsje8434u6HOWgUJk0ZdZj1mg0TeSVa0zMTyVP1QDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:18:48.553432Z","bundle_sha256":"988e9545132d16959c5d1c6f86b9b87784713488d6f5e4eb69836351b8e08e44"}}