{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RYKEHKHDGZPCQTWSI52S534CEV","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":"e5b50effdbec7112c994c5296d3fb4310bc6637b54ccd78700f842449e8dcd32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T02:20:00Z","title_canon_sha256":"a8f9555c1716b9d81cec380fc22e316e94552307951f3ad30327dc69f1009efa"},"schema_version":"1.0","source":{"id":"1708.00133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00133","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00133v2","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00133","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"RYKEHKHDGZPC","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RYKEHKHDGZPCQTWS","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RYKEHKHD","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:b21044a5a65b74b7f1b817d3b3195d76a523c7c1c1811879ae47eeedcffacf24","target":"graph","created_at":"2026-05-17T23:58:59Z","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 paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized policy representations that work across domains remains a challenging problem. We demonstrate that textual descriptions of environments provide a compact intermediate channel to facilitate effective policy transfer. Specifically, by learning to ground the meaning of text to the dynamics of the environment such as transitions and rewards, an autonomous agent can effectively bootstrap policy learning on a ","authors_text":"Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T02:20:00Z","title":"Grounding Language for Transfer in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00133","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:a07a1b68819941da153ddc15951b250a08c794cb85fb1f66d316e84cb27ed2db","target":"record","created_at":"2026-05-17T23:58:59Z","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":"e5b50effdbec7112c994c5296d3fb4310bc6637b54ccd78700f842449e8dcd32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T02:20:00Z","title_canon_sha256":"a8f9555c1716b9d81cec380fc22e316e94552307951f3ad30327dc69f1009efa"},"schema_version":"1.0","source":{"id":"1708.00133","kind":"arxiv","version":2}},"canonical_sha256":"8e1443a8e3365e284ed247752eef822545445f80524d407fa5ece789a89be1b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e1443a8e3365e284ed247752eef822545445f80524d407fa5ece789a89be1b4","first_computed_at":"2026-05-17T23:58:59.397575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:59.397575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GM4LH6dH1N0ZqDWGP8fQuTZZSw1fxZc17+AYhKjbTxojsOQHt1c815ePd66h0t7ahv6LJi1qZ53BSho5D95fAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:59.398103Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a07a1b68819941da153ddc15951b250a08c794cb85fb1f66d316e84cb27ed2db","sha256:b21044a5a65b74b7f1b817d3b3195d76a523c7c1c1811879ae47eeedcffacf24"],"state_sha256":"9417be36874267d6dbebf7d03523c0b97ddcbffb1dfeeb8ab1842057dc7968f1"}