{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LLKGCTLHWHLS22L4KV4IEDN3SH","short_pith_number":"pith:LLKGCTLH","canonical_record":{"source":{"id":"2007.06159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T02:52:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0a519743fc18788887d73cdd5d695fc3ae6dbe8b1abc91ccfaaca2474434503a","abstract_canon_sha256":"886c4578ca5837efdc4a9cf723b479638222e85a9a8d25e78ccf9f6e7b292e84"},"schema_version":"1.0"},"canonical_sha256":"5ad4614d67b1d72d697c5578820dbb91ffd0332c529c019b4bf5b2dad17d2f0b","source":{"kind":"arxiv","id":"2007.06159","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06159","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06159v2","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06159","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"LLKGCTLHWHLS","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_16","alias_value":"LLKGCTLHWHLS22L4","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_8","alias_value":"LLKGCTLH","created_at":"2026-07-05T01:44:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LLKGCTLHWHLS22L4KV4IEDN3SH","target":"record","payload":{"canonical_record":{"source":{"id":"2007.06159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T02:52:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0a519743fc18788887d73cdd5d695fc3ae6dbe8b1abc91ccfaaca2474434503a","abstract_canon_sha256":"886c4578ca5837efdc4a9cf723b479638222e85a9a8d25e78ccf9f6e7b292e84"},"schema_version":"1.0"},"canonical_sha256":"5ad4614d67b1d72d697c5578820dbb91ffd0332c529c019b4bf5b2dad17d2f0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:15.077827Z","signature_b64":"5CM5Km4JYlz4cTggDsrntsWuh5oIYzIgxC+U8xfc0/2DA753CT7jMeWWy+v3UqJD+8HFwCZ2xtXoGdpieKu0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad4614d67b1d72d697c5578820dbb91ffd0332c529c019b4bf5b2dad17d2f0b","last_reissued_at":"2026-07-05T01:44:15.077359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:15.077359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.06159","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":"2026-07-05T01:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1z5f2oujGVCkv2jvx/t7sMTyKVsLsGp4gq0C4OgXWnu/UwEdBhMkfRW6vDj2lk89uAmYnjNxXFtqvSA0QDDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:19:02.649604Z"},"content_sha256":"73ca4726008df9fef47bd8aee5b57ae2b60ae92999cdb833c66447e2c6bb3585","schema_version":"1.0","event_id":"sha256:73ca4726008df9fef47bd8aee5b57ae2b60ae92999cdb833c66447e2c6bb3585"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LLKGCTLHWHLS22L4KV4IEDN3SH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Yuguang Yue, Zhendong Wang","submitted_at":"2020-07-13T02:52:18Z","abstract_excerpt":"To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. We adopt a distributional perspective on the discounted cumulative return and model it with a state-action-dependent implicit distribution, which is approximated by the DGNs that take state-action pairs and random noises as their input. Moreover, we use the SIA to provide a semi-implicit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06159","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/2007.06159/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":"2026-07-05T01:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZKco0ZE4bC6heaxeTSqNyh4VJA6wXizyHwb+2PUOAI5UmDXT1tDS5Xi6uKXgnQzc1C64Z50VCf5zJ3nRUxuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:19:02.649989Z"},"content_sha256":"7b2653703c0f07bd337748a0f947fed872c77d2aa5727c08c637cdcdf7c8d67f","schema_version":"1.0","event_id":"sha256:7b2653703c0f07bd337748a0f947fed872c77d2aa5727c08c637cdcdf7c8d67f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/bundle.json","state_url":"https://pith.science/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/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":"2026-07-09T02:19:02Z","links":{"resolver":"https://pith.science/pith/LLKGCTLHWHLS22L4KV4IEDN3SH","bundle":"https://pith.science/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/bundle.json","state":"https://pith.science/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLKGCTLHWHLS22L4KV4IEDN3SH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LLKGCTLHWHLS22L4KV4IEDN3SH","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":"886c4578ca5837efdc4a9cf723b479638222e85a9a8d25e78ccf9f6e7b292e84","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T02:52:18Z","title_canon_sha256":"0a519743fc18788887d73cdd5d695fc3ae6dbe8b1abc91ccfaaca2474434503a"},"schema_version":"1.0","source":{"id":"2007.06159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06159","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06159v2","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06159","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"LLKGCTLHWHLS","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_16","alias_value":"LLKGCTLHWHLS22L4","created_at":"2026-07-05T01:44:15Z"},{"alias_kind":"pith_short_8","alias_value":"LLKGCTLH","created_at":"2026-07-05T01:44:15Z"}],"graph_snapshots":[{"event_id":"sha256:7b2653703c0f07bd337748a0f947fed872c77d2aa5727c08c637cdcdf7c8d67f","target":"graph","created_at":"2026-07-05T01:44:15Z","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/2007.06159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. We adopt a distributional perspective on the discounted cumulative return and model it with a state-action-dependent implicit distribution, which is approximated by the DGNs that take state-action pairs and random noises as their input. Moreover, we use the SIA to provide a semi-implicit ","authors_text":"Mingyuan Zhou, Yuguang Yue, Zhendong Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T02:52:18Z","title":"Implicit Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06159","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":"sha256:73ca4726008df9fef47bd8aee5b57ae2b60ae92999cdb833c66447e2c6bb3585","target":"record","created_at":"2026-07-05T01:44:15Z","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":"886c4578ca5837efdc4a9cf723b479638222e85a9a8d25e78ccf9f6e7b292e84","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T02:52:18Z","title_canon_sha256":"0a519743fc18788887d73cdd5d695fc3ae6dbe8b1abc91ccfaaca2474434503a"},"schema_version":"1.0","source":{"id":"2007.06159","kind":"arxiv","version":2}},"canonical_sha256":"5ad4614d67b1d72d697c5578820dbb91ffd0332c529c019b4bf5b2dad17d2f0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ad4614d67b1d72d697c5578820dbb91ffd0332c529c019b4bf5b2dad17d2f0b","first_computed_at":"2026-07-05T01:44:15.077359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:15.077359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CM5Km4JYlz4cTggDsrntsWuh5oIYzIgxC+U8xfc0/2DA753CT7jMeWWy+v3UqJD+8HFwCZ2xtXoGdpieKu0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:15.077827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73ca4726008df9fef47bd8aee5b57ae2b60ae92999cdb833c66447e2c6bb3585","sha256:7b2653703c0f07bd337748a0f947fed872c77d2aa5727c08c637cdcdf7c8d67f"],"state_sha256":"19c4e5cdab71bc0cdf9a9663822909391125cb45c4346baab630bb92821c2d5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dR7EhhqX/TPw+g5EIHnCl2Zg1H41TkM3LWyYJhEXBUNvebHH9zsTWMXicmkZdvvsZnk0ZKr7Bj4chBQhCMlYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:19:02.652440Z","bundle_sha256":"088727cbe6a94f040ab6929ce0719bba4db556a243bb069600dd349f1cd81cee"}}