{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FWOJY72UZSLB3SEK4VV37CEHBH","short_pith_number":"pith:FWOJY72U","canonical_record":{"source":{"id":"2006.07169","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-06-12T13:24:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"52dfd020dfefb565c1a82345474873218e10eee99a110bd87c546cbff992ef35","abstract_canon_sha256":"911a6907d0771f365962176d41c18887bd3c89530e3bf5e0eba20efa0760468a"},"schema_version":"1.0"},"canonical_sha256":"2d9c9c7f54cc961dc88ae56bbf888709d982ab0e81e4391a932b984b953e4f94","source":{"kind":"arxiv","id":"2006.07169","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07169","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07169v4","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07169","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"FWOJY72UZSLB","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWOJY72UZSLB3SEK","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWOJY72U","created_at":"2026-07-05T02:41:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FWOJY72UZSLB3SEK4VV37CEHBH","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07169","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-06-12T13:24:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"52dfd020dfefb565c1a82345474873218e10eee99a110bd87c546cbff992ef35","abstract_canon_sha256":"911a6907d0771f365962176d41c18887bd3c89530e3bf5e0eba20efa0760468a"},"schema_version":"1.0"},"canonical_sha256":"2d9c9c7f54cc961dc88ae56bbf888709d982ab0e81e4391a932b984b953e4f94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:28.013705Z","signature_b64":"kZnkQlYvl+H/BuOiNW69YijjSlxp8RA5JioWZr5JiKN2RgYqgYYzJnZFgJb6BxpgkAPxqJLFrlZMCyz3aWG8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9c9c7f54cc961dc88ae56bbf888709d982ab0e81e4391a932b984b953e4f94","last_reissued_at":"2026-07-05T02:41:28.013182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:28.013182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07169","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqFw6eWD/vqm/2+/4xIPbFHMpKdRe8i66VIj1L+1Mlnti3OVTQDij6BzdTLQ19CnVnr7VagTUtUe0DtSdOrdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:42:27.914960Z"},"content_sha256":"288d8d1ed5242278c3defb0ac21fe58e49aa86ebc378c38e454df0365a92ddca","schema_version":"1.0","event_id":"sha256:288d8d1ed5242278c3defb0ac21fe58e49aa86ebc378c38e454df0365a92ddca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FWOJY72UZSLB3SEK4VV37CEHBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Filippos Christianos, Lukas Sch\\\"afer, Stefano V. Albrecht","submitted_at":"2020-06-12T13:24:50Z","abstract_excerpt":"Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called Shared Experience Actor-Critic (SEAC), applies experience sharing in an actor-critic framework. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms two baselines and two state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07169","kind":"arxiv","version":4},"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/2006.07169/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":"2026-07-05T02:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dd6+ms7XfMuJhMoKISH8L0lHfzDJlWB4wYIswuMXTVA+5pATzpp0aDPgHPW9Ifs9jIuwsHx03Ccsh5MB1vxMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:42:27.915463Z"},"content_sha256":"2050e21c9fb80f0b44c13eb7679a6d6071bd528cd3bd8068c36b018ce6c33e48","schema_version":"1.0","event_id":"sha256:2050e21c9fb80f0b44c13eb7679a6d6071bd528cd3bd8068c36b018ce6c33e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWOJY72UZSLB3SEK4VV37CEHBH/bundle.json","state_url":"https://pith.science/pith/FWOJY72UZSLB3SEK4VV37CEHBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWOJY72UZSLB3SEK4VV37CEHBH/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":"2026-07-31T15:42:27Z","links":{"resolver":"https://pith.science/pith/FWOJY72UZSLB3SEK4VV37CEHBH","bundle":"https://pith.science/pith/FWOJY72UZSLB3SEK4VV37CEHBH/bundle.json","state":"https://pith.science/pith/FWOJY72UZSLB3SEK4VV37CEHBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWOJY72UZSLB3SEK4VV37CEHBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FWOJY72UZSLB3SEK4VV37CEHBH","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":"911a6907d0771f365962176d41c18887bd3c89530e3bf5e0eba20efa0760468a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-06-12T13:24:50Z","title_canon_sha256":"52dfd020dfefb565c1a82345474873218e10eee99a110bd87c546cbff992ef35"},"schema_version":"1.0","source":{"id":"2006.07169","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07169","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07169v4","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07169","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"FWOJY72UZSLB","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWOJY72UZSLB3SEK","created_at":"2026-07-05T02:41:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWOJY72U","created_at":"2026-07-05T02:41:28Z"}],"graph_snapshots":[{"event_id":"sha256:2050e21c9fb80f0b44c13eb7679a6d6071bd528cd3bd8068c36b018ce6c33e48","target":"graph","created_at":"2026-07-05T02:41:28Z","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/2006.07169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called Shared Experience Actor-Critic (SEAC), applies experience sharing in an actor-critic framework. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms two baselines and two state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, ","authors_text":"Filippos Christianos, Lukas Sch\\\"afer, Stefano V. Albrecht","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-06-12T13:24:50Z","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07169","kind":"arxiv","version":4},"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":"sha256:288d8d1ed5242278c3defb0ac21fe58e49aa86ebc378c38e454df0365a92ddca","target":"record","created_at":"2026-07-05T02:41:28Z","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":"911a6907d0771f365962176d41c18887bd3c89530e3bf5e0eba20efa0760468a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-06-12T13:24:50Z","title_canon_sha256":"52dfd020dfefb565c1a82345474873218e10eee99a110bd87c546cbff992ef35"},"schema_version":"1.0","source":{"id":"2006.07169","kind":"arxiv","version":4}},"canonical_sha256":"2d9c9c7f54cc961dc88ae56bbf888709d982ab0e81e4391a932b984b953e4f94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d9c9c7f54cc961dc88ae56bbf888709d982ab0e81e4391a932b984b953e4f94","first_computed_at":"2026-07-05T02:41:28.013182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:28.013182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kZnkQlYvl+H/BuOiNW69YijjSlxp8RA5JioWZr5JiKN2RgYqgYYzJnZFgJb6BxpgkAPxqJLFrlZMCyz3aWG8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:28.013705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07169","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:288d8d1ed5242278c3defb0ac21fe58e49aa86ebc378c38e454df0365a92ddca","sha256:2050e21c9fb80f0b44c13eb7679a6d6071bd528cd3bd8068c36b018ce6c33e48"],"state_sha256":"d2ad7578afa24225f2bc1105ec3a163c5ec556809d346f5922e431b76a90dd61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbYVAVxEZMMr89WDl1p8d/a+Q3yR+G1MAX9Wgt7fgx+AJKv10JsyqPVoYXFXXuk2qKFI6gjtizv2lkfphXaGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:42:27.920713Z","bundle_sha256":"6743e0e945f7e440b3e401d391921a5fb84f4d1ef10c87648dd765aec74b8d1b"}}