{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:M5YZAVN2SURFIF6UVPWQDSS5Y4","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":"77f5636bf57e70196079678f37057702b35fde2bb9f777f53e534f428411e9b0","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-26T19:23:54Z","title_canon_sha256":"a5938598f0351b54e041a8cbd4241fddb412816b6304778f94213d596b864c3a"},"schema_version":"1.0","source":{"id":"1707.08616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.08616","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"1707.08616v2","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08616","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"M5YZAVN2SURF","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"M5YZAVN2SURFIF6U","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"M5YZAVN2","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:4c830c478fbb3abbea56ac33f03ef7596e9026c5df17b927cff337aa8d257c0e","target":"graph","created_at":"2026-05-18T00:35:13Z","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":"In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action information. We then use this learned model to guide agent exploration using a modified version of policy shaping to make it more effective at learning in unseen environments. We evaluate this technique using the popular arcade game, Frogger, under ideal and non-ideal conditions. This eval","authors_text":"Brent Harrison, Mark O. Riedl, Upol Ehsan","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-26T19:23:54Z","title":"Guiding Reinforcement Learning Exploration Using Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08616","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":"sha256:962fe9caa4b3be0d42eecce46d7b12cfc4ee12171833c541e77bd5982f2da4b6","target":"record","created_at":"2026-05-18T00:35:13Z","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":"77f5636bf57e70196079678f37057702b35fde2bb9f777f53e534f428411e9b0","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-26T19:23:54Z","title_canon_sha256":"a5938598f0351b54e041a8cbd4241fddb412816b6304778f94213d596b864c3a"},"schema_version":"1.0","source":{"id":"1707.08616","kind":"arxiv","version":2}},"canonical_sha256":"67719055ba95225417d4abed01ca5dc707539e787fa3f9c53c8cad0008792087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67719055ba95225417d4abed01ca5dc707539e787fa3f9c53c8cad0008792087","first_computed_at":"2026-05-18T00:35:13.527554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:13.527554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8ACHVtU0P4yyVJ5T+ffnjKytqYo5ZBB/h4qqQTNs+JNQpgsxqFh2PhAmqRUtLZzQeOJot/UQUWZ7E30y7xMCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:13.528146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.08616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:962fe9caa4b3be0d42eecce46d7b12cfc4ee12171833c541e77bd5982f2da4b6","sha256:4c830c478fbb3abbea56ac33f03ef7596e9026c5df17b927cff337aa8d257c0e"],"state_sha256":"adfd314bacca710a180c330e917d0dc53d32eab3c2a25e446dd57cc00ccfb6b0"}