{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DWHIYUUEKJ5ZNHAD54627ALKQQ","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":"cb98131565dec764e0be9977e211dbbecb96f676201409f575e49d2a34348d25","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T21:53:11Z","title_canon_sha256":"88526cc0e0f04414725f16b2a4fff24aad4365b92d3f6c589f04bf5a64e91f04"},"schema_version":"1.0","source":{"id":"2205.05784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05784","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05784v1","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05784","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"DWHIYUUEKJ5Z","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"DWHIYUUEKJ5ZNHAD","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"DWHIYUUE","created_at":"2026-07-05T04:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:801ec6bcbae064f3a9c5ddbb586cf4b2f498d990547263a563aa4cd56407c85a","target":"graph","created_at":"2026-07-05T04:22:41Z","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/2205.05784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditionally, learning from human demonstrations via direct behavior cloning can lead to high-performance policies given that the algorithm has access to large amounts of high-quality data covering the most likely scenarios to be encountered when the agent is operating. However, in real-world scenarios, expert data is limited and it is desired to train an agent that learns a behavior policy general enough to handle situations that were not demonstrated by the human expert. Another alternative is to learn these policies with no supervision via deep reinforcement learning, however, these algori","authors_text":"Anjon Basak, Derrik E. Asher, James Hare, John Richardson, Mark Mittrick, Nicholas Waytowich, Vinicius G. Goecks","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T21:53:11Z","title":"Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05784","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:a6fae469325913927453c1151ac9304d237124f39cc5513b9a622afcac528689","target":"record","created_at":"2026-07-05T04:22:41Z","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":"cb98131565dec764e0be9977e211dbbecb96f676201409f575e49d2a34348d25","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T21:53:11Z","title_canon_sha256":"88526cc0e0f04414725f16b2a4fff24aad4365b92d3f6c589f04bf5a64e91f04"},"schema_version":"1.0","source":{"id":"2205.05784","kind":"arxiv","version":1}},"canonical_sha256":"1d8e8c5284527b969c03ef3daf816a840f7fa6db0a92d749328d9cffc88f29ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d8e8c5284527b969c03ef3daf816a840f7fa6db0a92d749328d9cffc88f29ef","first_computed_at":"2026-07-05T04:22:41.768686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:41.768686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2OeVL5P9EOn9RzgvF1LdcGQ0StgoIiMjYJjjQGu7/YfXbssFvaWI/xODLGt8sgvgL6xtPUfDRNGQOSyqXTdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:41.769167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6fae469325913927453c1151ac9304d237124f39cc5513b9a622afcac528689","sha256:801ec6bcbae064f3a9c5ddbb586cf4b2f498d990547263a563aa4cd56407c85a"],"state_sha256":"afd1ca21fb6cb04c003a19acb97d4a763e97c2e088af0772d09d5c16b6133272"}