{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SYCGCFZ7MK2PKJCFA6DGUG2IZO","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":"f5277a05114847331c7844f1acb07af14b97575becbfe6f6d24bfc3082b6fdf1","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-25T19:19:42Z","title_canon_sha256":"ba9bef4292a479b7a2f5a734515cb1d8c311df079d6bbe19cb676ae1377fce85"},"schema_version":"1.0","source":{"id":"1907.11703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11703","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11703v1","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11703","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"SYCGCFZ7MK2P","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SYCGCFZ7MK2PKJCF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SYCGCFZ7","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:1d99acc90a1ff8ab8e313a8de92658f8a29c342949e9eae87e78dfe1bb08b13d","target":"graph","created_at":"2026-05-17T23:39:23Z","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 has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrator to improve sample efficiency in a domain with sparse, delayed, and possibly deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. We propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with a small number rollouts, can be integrated within asynchronous distributed deep reinfor","authors_text":"Bilal Kartal, Matthew E. Taylor, Pablo Hernandez-Leal","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-25T19:19:42Z","title":"Action Guidance with MCTS for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11703","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":"sha256:698af3cd8334c20f2754a6cf6d7f3aa23947ce1e65c098d04623025be979a331","target":"record","created_at":"2026-05-17T23:39:23Z","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":"f5277a05114847331c7844f1acb07af14b97575becbfe6f6d24bfc3082b6fdf1","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-25T19:19:42Z","title_canon_sha256":"ba9bef4292a479b7a2f5a734515cb1d8c311df079d6bbe19cb676ae1377fce85"},"schema_version":"1.0","source":{"id":"1907.11703","kind":"arxiv","version":1}},"canonical_sha256":"960461173f62b4f5244507866a1b48cb85ac3516339b349e1042d4f3b3164b0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"960461173f62b4f5244507866a1b48cb85ac3516339b349e1042d4f3b3164b0e","first_computed_at":"2026-05-17T23:39:23.336523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:23.336523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdp04Mi6Dm7oj1Vr9MLxsoa//z2ps6GV2uqFg0AFEgAwhFSZ/9NcyFN9C5b6FGBb4kzeciPPzHmceUOZbyRyDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:23.337132Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:698af3cd8334c20f2754a6cf6d7f3aa23947ce1e65c098d04623025be979a331","sha256:1d99acc90a1ff8ab8e313a8de92658f8a29c342949e9eae87e78dfe1bb08b13d"],"state_sha256":"18d28c6e141c5dd630f11e9496732fea69496db3027291caf09cfdbc6a810971"}