{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FURYR3ES3VTJSYJCZB62LM657G","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":"f815bcfc290b4d21d776a0b5dfc091100f0ce21b2d3a1b69f88ba7d2a4c6442a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-12T17:42:21Z","title_canon_sha256":"96d77c41e9085f174e26b221755cab4b5cfad60ce0b3548b726c128fc9c7ccac"},"schema_version":"1.0","source":{"id":"1709.03969","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03969","created_at":"2026-07-05T02:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03969v2","created_at":"2026-07-05T02:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03969","created_at":"2026-07-05T02:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"FURYR3ES3VTJ","created_at":"2026-07-05T02:51:34Z"},{"alias_kind":"pith_short_16","alias_value":"FURYR3ES3VTJSYJC","created_at":"2026-07-05T02:51:34Z"},{"alias_kind":"pith_short_8","alias_value":"FURYR3ES","created_at":"2026-07-05T02:51:34Z"}],"graph_snapshots":[{"event_id":"sha256:22ff551910f2ec12c67b7ca7f7cabe5e254a2f2e3a65905026554b9a84c7e9db","target":"graph","created_at":"2026-07-05T02:51:34Z","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/1709.03969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent's environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation usin","authors_text":"Aaron Keech, Brent Harrison, Mark O. Riedl, Zhiyu Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-12T17:42:21Z","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03969","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:eaae345f480580c9acfebaf3e6888c6f9a5f087028226d764518f43ea7d3bba7","target":"record","created_at":"2026-07-05T02:51:34Z","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":"f815bcfc290b4d21d776a0b5dfc091100f0ce21b2d3a1b69f88ba7d2a4c6442a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-12T17:42:21Z","title_canon_sha256":"96d77c41e9085f174e26b221755cab4b5cfad60ce0b3548b726c128fc9c7ccac"},"schema_version":"1.0","source":{"id":"1709.03969","kind":"arxiv","version":2}},"canonical_sha256":"2d2388ec92dd66996122c87da5b3ddf9bd6a406a75b2cd26eb143b7b472abd9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d2388ec92dd66996122c87da5b3ddf9bd6a406a75b2cd26eb143b7b472abd9c","first_computed_at":"2026-07-05T02:51:34.831353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:51:34.831353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnWSqKqfWvcVUVGRSndaDoyR2TOW9VjYUtCxHpOwPA1VOOHCBUR+xHlsPF5NW6VGK27hS+e0vwmQg0cROUzrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:51:34.831801Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03969","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaae345f480580c9acfebaf3e6888c6f9a5f087028226d764518f43ea7d3bba7","sha256:22ff551910f2ec12c67b7ca7f7cabe5e254a2f2e3a65905026554b9a84c7e9db"],"state_sha256":"61201754c6120ad972b1f29d30fabb05950dd8ef1edc5d73d266baa46abd62d2"}