{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KBJ5S7LDSHDUFN7MAAZEXYOQMY","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":"291c1295ab405ffe0f3d6af971bbeef77c3bfc4403f20f7042606ca12dda8e36","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-12T23:46:16Z","title_canon_sha256":"ee2117358e796cbc2df38a1519a5b6fd381ceda64a40583f882141cb3c3217aa"},"schema_version":"1.0","source":{"id":"2003.06066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.06066","created_at":"2026-07-05T00:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"2003.06066v1","created_at":"2026-07-05T00:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06066","created_at":"2026-07-05T00:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"KBJ5S7LDSHDU","created_at":"2026-07-05T00:47:43Z"},{"alias_kind":"pith_short_16","alias_value":"KBJ5S7LDSHDUFN7M","created_at":"2026-07-05T00:47:43Z"},{"alias_kind":"pith_short_8","alias_value":"KBJ5S7LD","created_at":"2026-07-05T00:47:43Z"}],"graph_snapshots":[{"event_id":"sha256:46a364faf1377f8a71f33c93194edbed96f78387b59c25b0e02669603941e907","target":"graph","created_at":"2026-07-05T00:47:43Z","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/2003.06066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame ObtainDiamond with only 8M frames of environment interaction. We propose a training procedure where policy networks are first trained on human data and later fine-tuned by reinforcement learning. Using a policy exploitation mechanism, experience replay and an additional loss against catastrophic forgetting, our best agent was able to achieve a mean score of 48. Ou","authors_text":"Christian Scheller, Manfred Vogel, Yanick Schraner","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-12T23:46:16Z","title":"Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06066","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":"sha256:6523165c83542684fe44edb75c975460579db43f0b2f28b42d25735b9bfc5a71","target":"record","created_at":"2026-07-05T00:47:43Z","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":"291c1295ab405ffe0f3d6af971bbeef77c3bfc4403f20f7042606ca12dda8e36","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-12T23:46:16Z","title_canon_sha256":"ee2117358e796cbc2df38a1519a5b6fd381ceda64a40583f882141cb3c3217aa"},"schema_version":"1.0","source":{"id":"2003.06066","kind":"arxiv","version":1}},"canonical_sha256":"5053d97d6391c742b7ec00324be1d066056f2d814536879d7a5f6ca66d7d8346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5053d97d6391c742b7ec00324be1d066056f2d814536879d7a5f6ca66d7d8346","first_computed_at":"2026-07-05T00:47:43.462628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:43.462628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S+X3PfEqgWinUlK+XhB6/1glexHbzTcEBixqEKeqaClDSCgjQuxMKB9Gvu+Bxlrn5LCbpP/3VKG3XmOsD56sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:43.463004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.06066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6523165c83542684fe44edb75c975460579db43f0b2f28b42d25735b9bfc5a71","sha256:46a364faf1377f8a71f33c93194edbed96f78387b59c25b0e02669603941e907"],"state_sha256":"284193f8a7a26167926b304193c0108bf02931f93539ee9a6a2cc7825a9630b6"}