{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AHSZPEDCEZTHRLQLAHRBRXHL2R","short_pith_number":"pith:AHSZPEDC","canonical_record":{"source":{"id":"1712.06180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-17T21:29:45Z","cross_cats_sorted":[],"title_canon_sha256":"b02a752636430489e9c2005483add2cf98f77bcda8ea5e701dcc827c08a155ce","abstract_canon_sha256":"68654347b909c4b5512ac5ab63c6d7ad619f68208338fb4fda0fe190d70a4fca"},"schema_version":"1.0"},"canonical_sha256":"01e5979062266678ae0b01e218dcebd44f4f8afb343bbcd08656664a171447ce","source":{"kind":"arxiv","id":"1712.06180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06180","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06180v1","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06180","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"AHSZPEDCEZTH","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AHSZPEDCEZTHRLQL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AHSZPEDC","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AHSZPEDCEZTHRLQLAHRBRXHL2R","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-17T21:29:45Z","cross_cats_sorted":[],"title_canon_sha256":"b02a752636430489e9c2005483add2cf98f77bcda8ea5e701dcc827c08a155ce","abstract_canon_sha256":"68654347b909c4b5512ac5ab63c6d7ad619f68208338fb4fda0fe190d70a4fca"},"schema_version":"1.0"},"canonical_sha256":"01e5979062266678ae0b01e218dcebd44f4f8afb343bbcd08656664a171447ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:50.919271Z","signature_b64":"fFaj/kKxrO4+MQzax3iURX6gBrS+Pb9VaBUxHk9yKfJf5EH7AeHgiWLLt39SmCgK418DrrL89OM05+UtunSRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e5979062266678ae0b01e218dcebd44f4f8afb343bbcd08656664a171447ce","last_reissued_at":"2026-05-18T00:27:50.918499Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:50.918499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06180","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":"2026-05-18T00:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kN4Qmq7gXi+eH0TtQElL1vqIyG5ZOKyJQmXvsyRwpybTV0C+4kVF/DV/eZFpJrsE+AjYuTkGcYXF/KgFj+AAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:27:11.411609Z"},"content_sha256":"4a63356691438c4eeb055667bd4489a72654e525f612807812a67153351d3e76","schema_version":"1.0","event_id":"sha256:4a63356691438c4eeb055667bd4489a72654e525f612807812a67153351d3e76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AHSZPEDCEZTHRLQLAHRBRXHL2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a Deep Reinforcement Learning Approach for Tower Line Wars","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","submitted_at":"2017-12-17T21:29:45Z","abstract_excerpt":"There have been numerous breakthroughs with reinforcement learning in the recent years, perhaps most notably on Deep Reinforcement Learning successfully playing and winning relatively advanced computer games. There is undoubtedly an anticipation that Deep Reinforcement Learning will play a major role when the first AI masters the complicated game plays needed to beat a professional Real-Time Strategy game player. For this to be possible, there needs to be a game environment that targets and fosters AI research, and specifically Deep Reinforcement Learning. Some game environments already exist,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06180","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":"2026-05-18T00:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7fjqwGFheS00+xq6esDYwNAm93XQa9mYVkwHjRVp+h1j7wTNET8vsplKnwgmb8ctfrlHbAlkuLFYAl8nlczAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:27:11.412240Z"},"content_sha256":"af3106908b27efb7415129f8ba5d197ef1449f9b451e490b02a9b61e7a964089","schema_version":"1.0","event_id":"sha256:af3106908b27efb7415129f8ba5d197ef1449f9b451e490b02a9b61e7a964089"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/bundle.json","state_url":"https://pith.science/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/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":"2026-05-22T04:27:11Z","links":{"resolver":"https://pith.science/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R","bundle":"https://pith.science/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/bundle.json","state":"https://pith.science/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHSZPEDCEZTHRLQLAHRBRXHL2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AHSZPEDCEZTHRLQLAHRBRXHL2R","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":"68654347b909c4b5512ac5ab63c6d7ad619f68208338fb4fda0fe190d70a4fca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-17T21:29:45Z","title_canon_sha256":"b02a752636430489e9c2005483add2cf98f77bcda8ea5e701dcc827c08a155ce"},"schema_version":"1.0","source":{"id":"1712.06180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06180","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06180v1","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06180","created_at":"2026-05-18T00:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"AHSZPEDCEZTH","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AHSZPEDCEZTHRLQL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AHSZPEDC","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:af3106908b27efb7415129f8ba5d197ef1449f9b451e490b02a9b61e7a964089","target":"graph","created_at":"2026-05-18T00:27:50Z","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":"There have been numerous breakthroughs with reinforcement learning in the recent years, perhaps most notably on Deep Reinforcement Learning successfully playing and winning relatively advanced computer games. There is undoubtedly an anticipation that Deep Reinforcement Learning will play a major role when the first AI masters the complicated game plays needed to beat a professional Real-Time Strategy game player. For this to be possible, there needs to be a game environment that targets and fosters AI research, and specifically Deep Reinforcement Learning. Some game environments already exist,","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-17T21:29:45Z","title":"Towards a Deep Reinforcement Learning Approach for Tower Line Wars"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06180","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":"sha256:4a63356691438c4eeb055667bd4489a72654e525f612807812a67153351d3e76","target":"record","created_at":"2026-05-18T00:27:50Z","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":"68654347b909c4b5512ac5ab63c6d7ad619f68208338fb4fda0fe190d70a4fca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-17T21:29:45Z","title_canon_sha256":"b02a752636430489e9c2005483add2cf98f77bcda8ea5e701dcc827c08a155ce"},"schema_version":"1.0","source":{"id":"1712.06180","kind":"arxiv","version":1}},"canonical_sha256":"01e5979062266678ae0b01e218dcebd44f4f8afb343bbcd08656664a171447ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e5979062266678ae0b01e218dcebd44f4f8afb343bbcd08656664a171447ce","first_computed_at":"2026-05-18T00:27:50.918499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:50.918499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fFaj/kKxrO4+MQzax3iURX6gBrS+Pb9VaBUxHk9yKfJf5EH7AeHgiWLLt39SmCgK418DrrL89OM05+UtunSRCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:50.919271Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a63356691438c4eeb055667bd4489a72654e525f612807812a67153351d3e76","sha256:af3106908b27efb7415129f8ba5d197ef1449f9b451e490b02a9b61e7a964089"],"state_sha256":"618965bbb4ab8666f1d67817d35f670ae37eb65569b5db5527956fa3ef04da39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KNaiyai3cXdfBkeLQSTAjiJVN1Yrinh90sLgzL/g4/geP9zr+8P/hmiTsJYhvibiYn25ol8BJPR/SWFek3SoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T04:27:11.415731Z","bundle_sha256":"30eea3570d9b3c552cdca2ed884197c2b6cf0baddbe8f1cf220e5037c438b503"}}