{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DCDAUJG4BOYSC6SS26EAV4QPGD","short_pith_number":"pith:DCDAUJG4","canonical_record":{"source":{"id":"2109.06668","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T13:16:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"36e9c2c37118394a7acb20f87c1db571ec366adb20ca280ee4dec488ceb98a87","abstract_canon_sha256":"88012c8556b4caf4815541c15eea2d3f0f0c34afc45daa4dd820114be105ab17"},"schema_version":"1.0"},"canonical_sha256":"18860a24dc0bb1217a52d7880af20f30d127f356670ea29c5c6b683b8a786aed","source":{"kind":"arxiv","id":"2109.06668","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06668","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06668v6","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06668","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"DCDAUJG4BOYS","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"DCDAUJG4BOYSC6SS","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"DCDAUJG4","created_at":"2026-07-05T05:38:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DCDAUJG4BOYSC6SS26EAV4QPGD","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06668","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T13:16:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"36e9c2c37118394a7acb20f87c1db571ec366adb20ca280ee4dec488ceb98a87","abstract_canon_sha256":"88012c8556b4caf4815541c15eea2d3f0f0c34afc45daa4dd820114be105ab17"},"schema_version":"1.0"},"canonical_sha256":"18860a24dc0bb1217a52d7880af20f30d127f356670ea29c5c6b683b8a786aed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:07.474272Z","signature_b64":"m5icCfmHLINII2AeZRXfDOwzQqFJ4RuG1TCK1Tc2jinmdoNTqg6eLqT7jUOXPzDfWxAYBr5euDjPMChv5ah7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18860a24dc0bb1217a52d7880af20f30d127f356670ea29c5c6b683b8a786aed","last_reissued_at":"2026-07-05T05:38:07.473781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:07.473781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06668","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDQkCuVPd2LIVgN51VIkNtTLXIwEN01OLBa69fSP+MFKViwJh4AnASqcvmKb7rxHngu3TJAU1xxH7hLyhgQlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:57:03.300828Z"},"content_sha256":"51c68f382b3113260f603e4bbabbc758f91af2c0c16f268d014dad46ac170f60","schema_version":"1.0","event_id":"sha256:51c68f382b3113260f603e4bbabbc758f91af2c0c16f268d014dad46ac170f60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DCDAUJG4BOYSC6SS26EAV4QPGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Chenjia Bai, Hongyao Tang, Jianye Hao, Jinyi Liu, Peng Liu, Tianpei Yang, Zhaopeng Meng, Zhen Wang","submitted_at":"2021-09-14T13:16:33Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomous vehicles, robotics, and so on. However, DRL and deep MARL agents are widely known to be sample inefficient that millions of interactions are usually needed even for relatively simple problem settings, thus preventing the wide application and deployment in real-industry scenarios. One bottleneck challenge behind is the well-known exploration problem, i.e., how efficiently exploring the environment and collecting in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06668","kind":"arxiv","version":6},"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/2109.06668/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":"2026-07-05T05:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qwqo4/75oi71YZ/LUv3QmOJl77YmUtBdt3+An2vcmmxrKrTDuKe51y9c7DrLcjhidrP0KpuZFfFg8qIhZtsSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:57:03.301392Z"},"content_sha256":"20fa0cba6b9be14e91f778f90e3ce2f00603ee698e8d8f1b3ecdd6b9156f8749","schema_version":"1.0","event_id":"sha256:20fa0cba6b9be14e91f778f90e3ce2f00603ee698e8d8f1b3ecdd6b9156f8749"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/bundle.json","state_url":"https://pith.science/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/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":"2026-08-18T05:57:03Z","links":{"resolver":"https://pith.science/pith/DCDAUJG4BOYSC6SS26EAV4QPGD","bundle":"https://pith.science/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/bundle.json","state":"https://pith.science/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DCDAUJG4BOYSC6SS26EAV4QPGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DCDAUJG4BOYSC6SS26EAV4QPGD","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":"88012c8556b4caf4815541c15eea2d3f0f0c34afc45daa4dd820114be105ab17","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T13:16:33Z","title_canon_sha256":"36e9c2c37118394a7acb20f87c1db571ec366adb20ca280ee4dec488ceb98a87"},"schema_version":"1.0","source":{"id":"2109.06668","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06668","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06668v6","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06668","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"DCDAUJG4BOYS","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"DCDAUJG4BOYSC6SS","created_at":"2026-07-05T05:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"DCDAUJG4","created_at":"2026-07-05T05:38:07Z"}],"graph_snapshots":[{"event_id":"sha256:20fa0cba6b9be14e91f778f90e3ce2f00603ee698e8d8f1b3ecdd6b9156f8749","target":"graph","created_at":"2026-07-05T05:38:07Z","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/2109.06668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomous vehicles, robotics, and so on. However, DRL and deep MARL agents are widely known to be sample inefficient that millions of interactions are usually needed even for relatively simple problem settings, thus preventing the wide application and deployment in real-industry scenarios. One bottleneck challenge behind is the well-known exploration problem, i.e., how efficiently exploring the environment and collecting in","authors_text":"Chenjia Bai, Hongyao Tang, Jianye Hao, Jinyi Liu, Peng Liu, Tianpei Yang, Zhaopeng Meng, Zhen Wang","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T13:16:33Z","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06668","kind":"arxiv","version":6},"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":"sha256:51c68f382b3113260f603e4bbabbc758f91af2c0c16f268d014dad46ac170f60","target":"record","created_at":"2026-07-05T05:38:07Z","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":"88012c8556b4caf4815541c15eea2d3f0f0c34afc45daa4dd820114be105ab17","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T13:16:33Z","title_canon_sha256":"36e9c2c37118394a7acb20f87c1db571ec366adb20ca280ee4dec488ceb98a87"},"schema_version":"1.0","source":{"id":"2109.06668","kind":"arxiv","version":6}},"canonical_sha256":"18860a24dc0bb1217a52d7880af20f30d127f356670ea29c5c6b683b8a786aed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18860a24dc0bb1217a52d7880af20f30d127f356670ea29c5c6b683b8a786aed","first_computed_at":"2026-07-05T05:38:07.473781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:07.473781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m5icCfmHLINII2AeZRXfDOwzQqFJ4RuG1TCK1Tc2jinmdoNTqg6eLqT7jUOXPzDfWxAYBr5euDjPMChv5ah7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:07.474272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06668","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c68f382b3113260f603e4bbabbc758f91af2c0c16f268d014dad46ac170f60","sha256:20fa0cba6b9be14e91f778f90e3ce2f00603ee698e8d8f1b3ecdd6b9156f8749"],"state_sha256":"c6b26ebc846d2a157dd738ebeabad657b04bfd876628fe9ec62222904eb7a72d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCWQwmf9/p/NQHRsC1ZtdH1XNUlT1AGctOOX4vnFK1PHQ0flXRxNVG8u1vj7ukIk2L6k2i35Qr0VuH2n7+uJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:57:03.306759Z","bundle_sha256":"06918aa6e838a7388dd9c7c390a0aea45a305ba121cb9bab22473191343d2a3e"}}