{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4YHYBT2HNJEIKRHH5QAVE5HVFW","short_pith_number":"pith:4YHYBT2H","canonical_record":{"source":{"id":"1905.08786","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-21T11:38:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4b52fd79b60a05fbbd691bc619069028e56d94b61943949ec7e1f5922b0fcdd6","abstract_canon_sha256":"cd312df43c861715ca20db7d149347cf97110a970b492462ab224240257ca22f"},"schema_version":"1.0"},"canonical_sha256":"e60f80cf476a488544e7ec015274f52da1d61f5fa95039359daf8f2e2dabc48d","source":{"kind":"arxiv","id":"1905.08786","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.08786","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"1905.08786v3","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08786","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"4YHYBT2HNJEI","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"4YHYBT2HNJEIKRHH","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"4YHYBT2H","created_at":"2026-07-05T01:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4YHYBT2HNJEIKRHH5QAVE5HVFW","target":"record","payload":{"canonical_record":{"source":{"id":"1905.08786","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-21T11:38:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4b52fd79b60a05fbbd691bc619069028e56d94b61943949ec7e1f5922b0fcdd6","abstract_canon_sha256":"cd312df43c861715ca20db7d149347cf97110a970b492462ab224240257ca22f"},"schema_version":"1.0"},"canonical_sha256":"e60f80cf476a488544e7ec015274f52da1d61f5fa95039359daf8f2e2dabc48d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:09.276747Z","signature_b64":"czdwEdSzJaXkE5HzMu/xdEUebhpNc6DhCxSGd2nMTvCJXOcyxIMGQd/Ua96I+/yyp2h1OtiJwGzF6telmwRoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e60f80cf476a488544e7ec015274f52da1d61f5fa95039359daf8f2e2dabc48d","last_reissued_at":"2026-07-05T01:05:09.276285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:09.276285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.08786","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJFpBj8WHdGuvfuuhlsKtAJDM2lmyZy8ptgCU4SYAWtcb2JMZzJNtWe86yqodQi2dSQY/jBODJtTLCkJnI3jDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:27:59.058462Z"},"content_sha256":"3816f02799a7b791ec21cd9bb0552a7d29884a13a548f3b9beb59eb199958e21","schema_version":"1.0","event_id":"sha256:3816f02799a7b791ec21cd9bb0552a7d29884a13a548f3b9beb59eb199958e21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4YHYBT2HNJEIKRHH5QAVE5HVFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Zhao, Volker Tresp, Xudong Sun","submitted_at":"2019-05-21T11:38:39Z","abstract_excerpt":"In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08786","kind":"arxiv","version":3},"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/1905.08786/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":"2026-07-05T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8km+fsA0iumAcwCgTY/dlrAR4LbV49VRj4vPM7KRLWOPCPxU4d3cgbsedun2EA82pZMhGz9fCkdm1oAbtz9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:27:59.058977Z"},"content_sha256":"6de7035fbd3721ab944ca56932e3232e644bd5d69118965c9de874f6fb756f7f","schema_version":"1.0","event_id":"sha256:6de7035fbd3721ab944ca56932e3232e644bd5d69118965c9de874f6fb756f7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/bundle.json","state_url":"https://pith.science/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/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":"2026-08-22T15:27:59Z","links":{"resolver":"https://pith.science/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW","bundle":"https://pith.science/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/bundle.json","state":"https://pith.science/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YHYBT2HNJEIKRHH5QAVE5HVFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4YHYBT2HNJEIKRHH5QAVE5HVFW","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":"cd312df43c861715ca20db7d149347cf97110a970b492462ab224240257ca22f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-21T11:38:39Z","title_canon_sha256":"4b52fd79b60a05fbbd691bc619069028e56d94b61943949ec7e1f5922b0fcdd6"},"schema_version":"1.0","source":{"id":"1905.08786","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.08786","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"1905.08786v3","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08786","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"4YHYBT2HNJEI","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"4YHYBT2HNJEIKRHH","created_at":"2026-07-05T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"4YHYBT2H","created_at":"2026-07-05T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:6de7035fbd3721ab944ca56932e3232e644bd5d69118965c9de874f6fb756f7f","target":"graph","created_at":"2026-07-05T01:05:09Z","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/1905.08786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. ","authors_text":"Rui Zhao, Volker Tresp, Xudong Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-21T11:38:39Z","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08786","kind":"arxiv","version":3},"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":"sha256:3816f02799a7b791ec21cd9bb0552a7d29884a13a548f3b9beb59eb199958e21","target":"record","created_at":"2026-07-05T01:05:09Z","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":"cd312df43c861715ca20db7d149347cf97110a970b492462ab224240257ca22f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-21T11:38:39Z","title_canon_sha256":"4b52fd79b60a05fbbd691bc619069028e56d94b61943949ec7e1f5922b0fcdd6"},"schema_version":"1.0","source":{"id":"1905.08786","kind":"arxiv","version":3}},"canonical_sha256":"e60f80cf476a488544e7ec015274f52da1d61f5fa95039359daf8f2e2dabc48d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e60f80cf476a488544e7ec015274f52da1d61f5fa95039359daf8f2e2dabc48d","first_computed_at":"2026-07-05T01:05:09.276285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:09.276285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"czdwEdSzJaXkE5HzMu/xdEUebhpNc6DhCxSGd2nMTvCJXOcyxIMGQd/Ua96I+/yyp2h1OtiJwGzF6telmwRoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:09.276747Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.08786","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3816f02799a7b791ec21cd9bb0552a7d29884a13a548f3b9beb59eb199958e21","sha256:6de7035fbd3721ab944ca56932e3232e644bd5d69118965c9de874f6fb756f7f"],"state_sha256":"86fc054db1ec86e45547e5a4440cefbf247efafe7d6f670457242d5e3b60414d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Me5Ait8xBFggvfLASgcEMa2eqXqL7Zpw1Ei40kENOP8gpyK38e6XhgqXApCGbfd67zUQgb0qdk0ptV2ft0JpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:27:59.064040Z","bundle_sha256":"bb43539666beb10e93d66522994d44cd035f21ca417b71eb41aa0d9e090f4c49"}}