{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:CKWHMI7H2DAUTCMGJ6LYECFC7R","short_pith_number":"pith:CKWHMI7H","canonical_record":{"source":{"id":"1610.02707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-09T19:08:36Z","cross_cats_sorted":[],"title_canon_sha256":"4002048e407dfba1061c953d8d37c17f407ba4a1eebf8061cd275f22205dbd57","abstract_canon_sha256":"8d6ab8c39c6455bfef420fa74f91c0648595dcf8f346f72c20cca2530fee2c11"},"schema_version":"1.0"},"canonical_sha256":"12ac7623e7d0c14989864f978208a2fc4ca78d9805cc3c5d6b1504554dc0cf15","source":{"kind":"arxiv","id":"1610.02707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02707","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02707v1","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02707","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"CKWHMI7H2DAU","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CKWHMI7H2DAUTCMG","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CKWHMI7H","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:CKWHMI7H2DAUTCMGJ6LYECFC7R","target":"record","payload":{"canonical_record":{"source":{"id":"1610.02707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-09T19:08:36Z","cross_cats_sorted":[],"title_canon_sha256":"4002048e407dfba1061c953d8d37c17f407ba4a1eebf8061cd275f22205dbd57","abstract_canon_sha256":"8d6ab8c39c6455bfef420fa74f91c0648595dcf8f346f72c20cca2530fee2c11"},"schema_version":"1.0"},"canonical_sha256":"12ac7623e7d0c14989864f978208a2fc4ca78d9805cc3c5d6b1504554dc0cf15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:50.907578Z","signature_b64":"OLVPqoSMHnb9bhHZXpkai5klFQtOTQv4JdFLBg+0hBwlA27oiibZvAJHHPFzJZGoKvW99uLzK0QpqCgrMDFcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ac7623e7d0c14989864f978208a2fc4ca78d9805cc3c5d6b1504554dc0cf15","last_reissued_at":"2026-05-18T01:02:50.907125Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:50.907125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.02707","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":"2026-05-18T01:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svYmwaRfBoFTIYU/eO6m9Lc/3F34Jq2Pz0x3IdsAjavnqrQPuRkYNqn9dgIVZ4IbQX7JEH9HykkJkuhFXjDuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:46.697055Z"},"content_sha256":"6cbf7ac73758e6fbbaa396b73d789ca9d71ed1d599b3447a72e26d39e06fe548","schema_version":"1.0","event_id":"sha256:6cbf7ac73758e6fbbaa396b73d789ca9d71ed1d599b3447a72e26d39e06fe548"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:CKWHMI7H2DAUTCMGJ6LYECFC7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Objective Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Diederik M. Roijers, Hossam Mossalam, Shimon Whiteson, Yannis M. Assael","submitted_at":"2016-10-09T19:08:36Z","abstract_excerpt":"We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02707","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":"2026-05-18T01:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ow1BMND1yq4ZOKJSEH3994bMYkw+hwHbAeB7cvscBq4Z45c58sU4BQUQ6t+YxaVZqnlb/PvWJyYYuLcBwCnlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:46.697453Z"},"content_sha256":"4a3b70176e013cef1988eb0a97986eb3690814f688a2ad1aee23a54d4bc16868","schema_version":"1.0","event_id":"sha256:4a3b70176e013cef1988eb0a97986eb3690814f688a2ad1aee23a54d4bc16868"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/bundle.json","state_url":"https://pith.science/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/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":"2026-05-27T15:56:46Z","links":{"resolver":"https://pith.science/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R","bundle":"https://pith.science/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/bundle.json","state":"https://pith.science/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKWHMI7H2DAUTCMGJ6LYECFC7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:CKWHMI7H2DAUTCMGJ6LYECFC7R","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":"8d6ab8c39c6455bfef420fa74f91c0648595dcf8f346f72c20cca2530fee2c11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-09T19:08:36Z","title_canon_sha256":"4002048e407dfba1061c953d8d37c17f407ba4a1eebf8061cd275f22205dbd57"},"schema_version":"1.0","source":{"id":"1610.02707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02707","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02707v1","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02707","created_at":"2026-05-18T01:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"CKWHMI7H2DAU","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CKWHMI7H2DAUTCMG","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CKWHMI7H","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:4a3b70176e013cef1988eb0a97986eb3690814f688a2ad1aee23a54d4bc16868","target":"graph","created_at":"2026-05-18T01:02:50Z","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":"We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective rei","authors_text":"Diederik M. Roijers, Hossam Mossalam, Shimon Whiteson, Yannis M. Assael","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-09T19:08:36Z","title":"Multi-Objective Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02707","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":"sha256:6cbf7ac73758e6fbbaa396b73d789ca9d71ed1d599b3447a72e26d39e06fe548","target":"record","created_at":"2026-05-18T01:02:50Z","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":"8d6ab8c39c6455bfef420fa74f91c0648595dcf8f346f72c20cca2530fee2c11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-09T19:08:36Z","title_canon_sha256":"4002048e407dfba1061c953d8d37c17f407ba4a1eebf8061cd275f22205dbd57"},"schema_version":"1.0","source":{"id":"1610.02707","kind":"arxiv","version":1}},"canonical_sha256":"12ac7623e7d0c14989864f978208a2fc4ca78d9805cc3c5d6b1504554dc0cf15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ac7623e7d0c14989864f978208a2fc4ca78d9805cc3c5d6b1504554dc0cf15","first_computed_at":"2026-05-18T01:02:50.907125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:02:50.907125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OLVPqoSMHnb9bhHZXpkai5klFQtOTQv4JdFLBg+0hBwlA27oiibZvAJHHPFzJZGoKvW99uLzK0QpqCgrMDFcBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:02:50.907578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.02707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cbf7ac73758e6fbbaa396b73d789ca9d71ed1d599b3447a72e26d39e06fe548","sha256:4a3b70176e013cef1988eb0a97986eb3690814f688a2ad1aee23a54d4bc16868"],"state_sha256":"626e2529b13b58f6d07e8ed33fc91021a7b83da9c6230dff5b26ddd5ffaa042d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laZ0a4uZoOr6pekERsIi/aNAEy/SpE97uPsLLsd7+etr1rA7qCjv7AUwmyP9UdBOax3Eyn7Gb/ge9JYCfW07Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:56:46.700896Z","bundle_sha256":"e2fa93f755d0e65836f3c7a4e65321c8c50134666722e8caffc25f32e5f37809"}}