{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KS6RW67SRSSPBBLLY2L4SDNZHQ","short_pith_number":"pith:KS6RW67S","canonical_record":{"source":{"id":"1710.00336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"32060b062a0254a50e82baadd6e23f3aeea9a84db952249043537b31491d1290","abstract_canon_sha256":"9304300f71164b1e0109a65cb187cea8c18273fea3e7bca243844a43bc15f09e"},"schema_version":"1.0"},"canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","source":{"kind":"arxiv","id":"1710.00336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00336","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00336v2","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00336","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"pith_short_12","alias_value":"KS6RW67SRSSP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KS6RW67SRSSPBBLL","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KS6RW67S","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KS6RW67SRSSPBBLLY2L4SDNZHQ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.00336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"32060b062a0254a50e82baadd6e23f3aeea9a84db952249043537b31491d1290","abstract_canon_sha256":"9304300f71164b1e0109a65cb187cea8c18273fea3e7bca243844a43bc15f09e"},"schema_version":"1.0"},"canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:47.822684Z","signature_b64":"dvalGWXsQufENTzi4YY4DO7qgLoNoWzy3uaX8yOoEyINv72zeOdaRl/QTpPWgqd3IvJdObhkz2pVMkgCusYvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","last_reissued_at":"2026-05-18T00:33:47.822110Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:47.822110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.00336","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:33:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nyxU0fx5v9yYwFKyWLYV5xdg75H0dbvu2HrMfS4fPdj+uFmfnE8L9Qd5pMeie9y+lTKVuA7YN9xyIcWSBD1XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:22:02.124691Z"},"content_sha256":"aa523a73dcb6a6fa6dfbec2cd61573cb7c298a255de2c3236ee6b18154ac2b0a","schema_version":"1.0","event_id":"sha256:aa523a73dcb6a6fa6dfbec2cd61573cb7c298a255de2c3236ee6b18154ac2b0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KS6RW67SRSSPBBLLY2L4SDNZHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hangjun Ye, Xiangxiang Chu","submitted_at":"2017-10-01T11:43:10Z","abstract_excerpt":"Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00336","kind":"arxiv","version":2},"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":"2026-05-18T00:33:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urqNSEg1q2xRW7PFr6zF79bphgbLOdJHFmriWWUQ85N/2PbSlXmrqzWnH4SGNLI5/lZ1GEmUBI2CktNW61TjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:22:02.125050Z"},"content_sha256":"2ae9f40d3a99d649eae4e24ac39e5d849eb575e8424cdf34d68053963715d2cf","schema_version":"1.0","event_id":"sha256:2ae9f40d3a99d649eae4e24ac39e5d849eb575e8424cdf34d68053963715d2cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/bundle.json","state_url":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/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":"2026-06-01T05:22:02Z","links":{"resolver":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ","bundle":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/bundle.json","state":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KS6RW67SRSSPBBLLY2L4SDNZHQ","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":"9304300f71164b1e0109a65cb187cea8c18273fea3e7bca243844a43bc15f09e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","title_canon_sha256":"32060b062a0254a50e82baadd6e23f3aeea9a84db952249043537b31491d1290"},"schema_version":"1.0","source":{"id":"1710.00336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00336","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00336v2","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00336","created_at":"2026-05-18T00:33:47Z"},{"alias_kind":"pith_short_12","alias_value":"KS6RW67SRSSP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KS6RW67SRSSPBBLL","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KS6RW67S","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:2ae9f40d3a99d649eae4e24ac39e5d849eb575e8424cdf34d68053963715d2cf","target":"graph","created_at":"2026-05-18T00:33:47Z","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":"Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing wit","authors_text":"Hangjun Ye, Xiangxiang Chu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","title":"Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00336","kind":"arxiv","version":2},"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:aa523a73dcb6a6fa6dfbec2cd61573cb7c298a255de2c3236ee6b18154ac2b0a","target":"record","created_at":"2026-05-18T00:33:47Z","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":"9304300f71164b1e0109a65cb187cea8c18273fea3e7bca243844a43bc15f09e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","title_canon_sha256":"32060b062a0254a50e82baadd6e23f3aeea9a84db952249043537b31491d1290"},"schema_version":"1.0","source":{"id":"1710.00336","kind":"arxiv","version":2}},"canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","first_computed_at":"2026-05-18T00:33:47.822110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:47.822110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dvalGWXsQufENTzi4YY4DO7qgLoNoWzy3uaX8yOoEyINv72zeOdaRl/QTpPWgqd3IvJdObhkz2pVMkgCusYvBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:47.822684Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.00336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa523a73dcb6a6fa6dfbec2cd61573cb7c298a255de2c3236ee6b18154ac2b0a","sha256:2ae9f40d3a99d649eae4e24ac39e5d849eb575e8424cdf34d68053963715d2cf"],"state_sha256":"58d0851a2068f9492c17d158342ed30794af53374ac756e816c0e2a0a10643b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xAI+J1Pn1IHADVN/VIWV+I8i8PO+D0fu151G+V4pC3DwXjrNvtYdTn9cazk3WqL9yamTFkE6FwYwteMTNUrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:22:02.127194Z","bundle_sha256":"1025a1f6fead200f1a26dc475acf68af84f5bf3ac65d8115f3e333013ed794ea"}}