{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BLMY7JECZQKRZYQ34KIWTC56HC","short_pith_number":"pith:BLMY7JEC","canonical_record":{"source":{"id":"2302.02298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:42:42Z","cross_cats_sorted":[],"title_canon_sha256":"df2337b551bac46e467e591cb85a4d411fc8da02ac5a029975847ea94c1b6d7d","abstract_canon_sha256":"031cf87a9daf83846d48cb3468441342ee813d3b779e933ad74b1e1b8433e850"},"schema_version":"1.0"},"canonical_sha256":"0ad98fa482cc151ce21be291698bbe388065b0214ae016737eb206622de3b6fb","source":{"kind":"arxiv","id":"2302.02298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02298","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02298v1","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02298","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"BLMY7JECZQKR","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"BLMY7JECZQKRZYQ3","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"BLMY7JEC","created_at":"2026-07-05T05:38:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BLMY7JECZQKRZYQ34KIWTC56HC","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:42:42Z","cross_cats_sorted":[],"title_canon_sha256":"df2337b551bac46e467e591cb85a4d411fc8da02ac5a029975847ea94c1b6d7d","abstract_canon_sha256":"031cf87a9daf83846d48cb3468441342ee813d3b779e933ad74b1e1b8433e850"},"schema_version":"1.0"},"canonical_sha256":"0ad98fa482cc151ce21be291698bbe388065b0214ae016737eb206622de3b6fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:51.706724Z","signature_b64":"W66SpxlkwxKLsvQv+UuWvTBXF4+dRRSnskdGagMcbKXo5//rLiPr6Zoloivvo6nmgIbfjOR+4mzYMVYbSv+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad98fa482cc151ce21be291698bbe388065b0214ae016737eb206622de3b6fb","last_reissued_at":"2026-07-05T05:38:51.706255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:51.706255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02298","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":"2026-07-05T05:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VA+oUVo/u+AnUQmpyjt2K2lF3+E0TovqE7wAf1q27s9tpnSbCSw/4w9ru/ci7zgy3GeJ96+GZJmb5b22Oyg5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:24:55.166801Z"},"content_sha256":"1203e888405fb69f151ca3b164d2615e7be20d357533d6c203a3ccfd615cd665","schema_version":"1.0","event_id":"sha256:1203e888405fb69f151ca3b164d2615e7be20d357533d6c203a3ccfd615cd665"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BLMY7JECZQKRZYQ34KIWTC56HC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open Problems and Modern Solutions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Weiqin Chen","submitted_at":"2023-02-05T04:42:42Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved great success in solving complicated decision-making problems. Despite the successes, DRL is frequently criticized for many reasons, e.g., data inefficient, inflexible and intractable reward design. In this paper, we review two publications that investigate the mentioned issues of DRL and propose effective solutions. One designs the reward for human-robot collaboration by combining the manually designed extrinsic reward with a parameterized intrinsic reward function via the deterministic policy gradient, which improves the task performance and gua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02298","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/2302.02298/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":"2026-07-05T05:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+JUgN3Jc/RFBffrgOTTAbMy391dvGXoU++xPbysMyw3+drXgnWDX/Nv8NujmtWk7VeCfIn0hL9YhmV+MAqRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:24:55.167180Z"},"content_sha256":"88a38ae4350184bc131bd1710edeca07eb30252405ff722f5283202df300a444","schema_version":"1.0","event_id":"sha256:88a38ae4350184bc131bd1710edeca07eb30252405ff722f5283202df300a444"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLMY7JECZQKRZYQ34KIWTC56HC/bundle.json","state_url":"https://pith.science/pith/BLMY7JECZQKRZYQ34KIWTC56HC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLMY7JECZQKRZYQ34KIWTC56HC/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":"2026-07-07T09:24:55Z","links":{"resolver":"https://pith.science/pith/BLMY7JECZQKRZYQ34KIWTC56HC","bundle":"https://pith.science/pith/BLMY7JECZQKRZYQ34KIWTC56HC/bundle.json","state":"https://pith.science/pith/BLMY7JECZQKRZYQ34KIWTC56HC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLMY7JECZQKRZYQ34KIWTC56HC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BLMY7JECZQKRZYQ34KIWTC56HC","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":"031cf87a9daf83846d48cb3468441342ee813d3b779e933ad74b1e1b8433e850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:42:42Z","title_canon_sha256":"df2337b551bac46e467e591cb85a4d411fc8da02ac5a029975847ea94c1b6d7d"},"schema_version":"1.0","source":{"id":"2302.02298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02298","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02298v1","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02298","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"BLMY7JECZQKR","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"BLMY7JECZQKRZYQ3","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"BLMY7JEC","created_at":"2026-07-05T05:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:88a38ae4350184bc131bd1710edeca07eb30252405ff722f5283202df300a444","target":"graph","created_at":"2026-07-05T05:38:51Z","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/2302.02298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved great success in solving complicated decision-making problems. Despite the successes, DRL is frequently criticized for many reasons, e.g., data inefficient, inflexible and intractable reward design. In this paper, we review two publications that investigate the mentioned issues of DRL and propose effective solutions. One designs the reward for human-robot collaboration by combining the manually designed extrinsic reward with a parameterized intrinsic reward function via the deterministic policy gradient, which improves the task performance and gua","authors_text":"Weiqin Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:42:42Z","title":"Open Problems and Modern Solutions for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02298","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":"sha256:1203e888405fb69f151ca3b164d2615e7be20d357533d6c203a3ccfd615cd665","target":"record","created_at":"2026-07-05T05:38:51Z","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":"031cf87a9daf83846d48cb3468441342ee813d3b779e933ad74b1e1b8433e850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:42:42Z","title_canon_sha256":"df2337b551bac46e467e591cb85a4d411fc8da02ac5a029975847ea94c1b6d7d"},"schema_version":"1.0","source":{"id":"2302.02298","kind":"arxiv","version":1}},"canonical_sha256":"0ad98fa482cc151ce21be291698bbe388065b0214ae016737eb206622de3b6fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad98fa482cc151ce21be291698bbe388065b0214ae016737eb206622de3b6fb","first_computed_at":"2026-07-05T05:38:51.706255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:51.706255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W66SpxlkwxKLsvQv+UuWvTBXF4+dRRSnskdGagMcbKXo5//rLiPr6Zoloivvo6nmgIbfjOR+4mzYMVYbSv+fDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:51.706724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1203e888405fb69f151ca3b164d2615e7be20d357533d6c203a3ccfd615cd665","sha256:88a38ae4350184bc131bd1710edeca07eb30252405ff722f5283202df300a444"],"state_sha256":"c76bf32967d638f39f7fdb8715a46cffbbf8d6288ae0490ea0bd3a186c5012e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AvAh2OZmpP2dt+vcg2Dpie7aby0Oj51sOwsM82vTSK0XSz4RGn/XXBqhNLL5cP/06+DW68vS/WbP42TumjbmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:24:55.169718Z","bundle_sha256":"b60b3465f16bf4a09ff97770031f44701d2e78473f9f958386e3d696b1b15ff4"}}