{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7VVFXH6VNF4OAYMXM4D2OOBWNM","short_pith_number":"pith:7VVFXH6V","canonical_record":{"source":{"id":"1806.09605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T18:31:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1fbb43b9b92d9af14e787e74a3a6897028b2a7956b9b2bb7552171cbfc495ce5","abstract_canon_sha256":"46ab8b19d3148c6a077b7a2e8aa96258bcaa1fef8feff032b78620fe6bf53798"},"schema_version":"1.0"},"canonical_sha256":"fd6a5b9fd56978e061976707a738366b19973e2363a0718a4fd63347fd7b4498","source":{"kind":"arxiv","id":"1806.09605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09605","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09605v1","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09605","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"7VVFXH6VNF4O","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7VVFXH6VNF4OAYMX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7VVFXH6V","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7VVFXH6VNF4OAYMXM4D2OOBWNM","target":"record","payload":{"canonical_record":{"source":{"id":"1806.09605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T18:31:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1fbb43b9b92d9af14e787e74a3a6897028b2a7956b9b2bb7552171cbfc495ce5","abstract_canon_sha256":"46ab8b19d3148c6a077b7a2e8aa96258bcaa1fef8feff032b78620fe6bf53798"},"schema_version":"1.0"},"canonical_sha256":"fd6a5b9fd56978e061976707a738366b19973e2363a0718a4fd63347fd7b4498","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:23.949720Z","signature_b64":"9/PXvsPsX/0rQVGoY6UX+QLMuumAvwGbXcNsX+dpzFCuZt1uGDcl/C/OPppB3HJFl93HRdb2a9eW3mXEZEcaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd6a5b9fd56978e061976707a738366b19973e2363a0718a4fd63347fd7b4498","last_reissued_at":"2026-05-18T00:12:23.948922Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:23.948922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.09605","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":"2026-05-18T00:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKRAVvp/eXDisubijls5Ptgx4i8mpFTYI1oDpryNrg79lcZv4z24tgu5Cqe45TzmzGjoSQXFONt2OQlMSHKDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:34:04.458038Z"},"content_sha256":"51c26adc67dd9218e2e07620be86d5c25cfc60b9c2ad862cb66eb637630a2ac9","schema_version":"1.0","event_id":"sha256:51c26adc67dd9218e2e07620be86d5c25cfc60b9c2ad862cb66eb637630a2ac9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7VVFXH6VNF4OAYMXM4D2OOBWNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Many-Goals Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junhyuk Oh, Satinder Singh, Vivek Veeriah","submitted_at":"2018-06-22T18:31:24Z","abstract_excerpt":"All-goals updating exploits the off-policy nature of Q-learning to update all possible goals an agent could have from each transition in the world, and was introduced into Reinforcement Learning (RL) by Kaelbling (1993). In prior work this was mostly explored in small-state RL problems that allowed tabular representations and where all possible goals could be explicitly enumerated and learned separately. In this paper we empirically explore 3 different extensions of the idea of updating many (instead of all) goals in the context of RL with deep neural networks (or DeepRL for short). First, in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09605","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":""},"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":"2026-05-18T00:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qeV3RFx91AFL1n9imBa1kE5qqvJFDfeGNBSPa/AL388NW+d7lUmPBixS7eiFr502Lg78fgBNs194cegZEpHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:34:04.458785Z"},"content_sha256":"6084d9fe82365d7710f9986bef20bdd72a6813511d5429a039eda802cf853152","schema_version":"1.0","event_id":"sha256:6084d9fe82365d7710f9986bef20bdd72a6813511d5429a039eda802cf853152"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/bundle.json","state_url":"https://pith.science/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/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":"2026-06-10T06:34:04Z","links":{"resolver":"https://pith.science/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM","bundle":"https://pith.science/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/bundle.json","state":"https://pith.science/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VVFXH6VNF4OAYMXM4D2OOBWNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7VVFXH6VNF4OAYMXM4D2OOBWNM","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":"46ab8b19d3148c6a077b7a2e8aa96258bcaa1fef8feff032b78620fe6bf53798","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T18:31:24Z","title_canon_sha256":"1fbb43b9b92d9af14e787e74a3a6897028b2a7956b9b2bb7552171cbfc495ce5"},"schema_version":"1.0","source":{"id":"1806.09605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09605","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09605v1","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09605","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"7VVFXH6VNF4O","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7VVFXH6VNF4OAYMX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7VVFXH6V","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:6084d9fe82365d7710f9986bef20bdd72a6813511d5429a039eda802cf853152","target":"graph","created_at":"2026-05-18T00:12:23Z","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"},"paper":{"abstract_excerpt":"All-goals updating exploits the off-policy nature of Q-learning to update all possible goals an agent could have from each transition in the world, and was introduced into Reinforcement Learning (RL) by Kaelbling (1993). In prior work this was mostly explored in small-state RL problems that allowed tabular representations and where all possible goals could be explicitly enumerated and learned separately. In this paper we empirically explore 3 different extensions of the idea of updating many (instead of all) goals in the context of RL with deep neural networks (or DeepRL for short). First, in ","authors_text":"Junhyuk Oh, Satinder Singh, Vivek Veeriah","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T18:31:24Z","title":"Many-Goals Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09605","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":"sha256:51c26adc67dd9218e2e07620be86d5c25cfc60b9c2ad862cb66eb637630a2ac9","target":"record","created_at":"2026-05-18T00:12:23Z","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":"46ab8b19d3148c6a077b7a2e8aa96258bcaa1fef8feff032b78620fe6bf53798","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T18:31:24Z","title_canon_sha256":"1fbb43b9b92d9af14e787e74a3a6897028b2a7956b9b2bb7552171cbfc495ce5"},"schema_version":"1.0","source":{"id":"1806.09605","kind":"arxiv","version":1}},"canonical_sha256":"fd6a5b9fd56978e061976707a738366b19973e2363a0718a4fd63347fd7b4498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd6a5b9fd56978e061976707a738366b19973e2363a0718a4fd63347fd7b4498","first_computed_at":"2026-05-18T00:12:23.948922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:23.948922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9/PXvsPsX/0rQVGoY6UX+QLMuumAvwGbXcNsX+dpzFCuZt1uGDcl/C/OPppB3HJFl93HRdb2a9eW3mXEZEcaBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:23.949720Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.09605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c26adc67dd9218e2e07620be86d5c25cfc60b9c2ad862cb66eb637630a2ac9","sha256:6084d9fe82365d7710f9986bef20bdd72a6813511d5429a039eda802cf853152"],"state_sha256":"7e3cc7942990a08be52c40f8c7c8d7c150fb4bbbae16362013ca83d98a045fa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1FHdihr4E4XRZxuJ2eYneS0LXu/K3ZnUJOWD58AAi2LiwJccHPFZm8PUamofobs0dbII7rf5H6eHYXuFzN7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T06:34:04.461837Z","bundle_sha256":"f8251e5d04ce32d61c48675ad09baf225447fc106e8d3d7ca3bc1195fd7df16a"}}