{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TPBJV5RX76GPEJIXQGFZTF4GHQ","short_pith_number":"pith:TPBJV5RX","schema_version":"1.0","canonical_sha256":"9bc29af637ff8cf22517818b9997863c0d90931721a5f209fa9554e1ff5a13fc","source":{"kind":"arxiv","id":"2102.05714","version":2},"attestation_state":"computed","paper":{"title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emre Neftci, Jeffrey L. Krichmar, Jinwei Xing, Kexin Chen, Takashi Nagata, Xinyun Zou","submitted_at":"2021-02-10T19:38:14Z","abstract_excerpt":"Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.05714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-10T19:38:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50b02d1ef8ea8b678fe536df6502e01fc1f7204d069330e7b5c98b3b811fdd3c","abstract_canon_sha256":"47ac22b0c89f675c3e1e6a6deef5e0dcd6746de1249c6aa0bbd5faa77e9e7d54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:11.752238Z","signature_b64":"udo/OO6lirnwLKYw/BHWP5r1+mBk6GR5OwVEDxJzzGNDACXT+RiaKTCX0MGcoMJ6I2Zn/smya9jidDZDCKKyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bc29af637ff8cf22517818b9997863c0d90931721a5f209fa9554e1ff5a13fc","last_reissued_at":"2026-07-05T03:11:11.751802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:11.751802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emre Neftci, Jeffrey L. Krichmar, Jinwei Xing, Kexin Chen, Takashi Nagata, Xinyun Zou","submitted_at":"2021-02-10T19:38:14Z","abstract_excerpt":"Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05714","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.05714/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.05714","created_at":"2026-07-05T03:11:11.751855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05714v2","created_at":"2026-07-05T03:11:11.751855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05714","created_at":"2026-07-05T03:11:11.751855+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPBJV5RX76GP","created_at":"2026-07-05T03:11:11.751855+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPBJV5RX76GPEJIX","created_at":"2026-07-05T03:11:11.751855+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPBJV5RX","created_at":"2026-07-05T03:11:11.751855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08221","citing_title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ","json":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ.json","graph_json":"https://pith.science/api/pith-number/TPBJV5RX76GPEJIXQGFZTF4GHQ/graph.json","events_json":"https://pith.science/api/pith-number/TPBJV5RX76GPEJIXQGFZTF4GHQ/events.json","paper":"https://pith.science/paper/TPBJV5RX"},"agent_actions":{"view_html":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ","download_json":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ.json","view_paper":"https://pith.science/paper/TPBJV5RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05714&json=true","fetch_graph":"https://pith.science/api/pith-number/TPBJV5RX76GPEJIXQGFZTF4GHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TPBJV5RX76GPEJIXQGFZTF4GHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ/action/storage_attestation","attest_author":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ/action/author_attestation","sign_citation":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ/action/citation_signature","submit_replication":"https://pith.science/pith/TPBJV5RX76GPEJIXQGFZTF4GHQ/action/replication_record"}},"created_at":"2026-07-05T03:11:11.751855+00:00","updated_at":"2026-07-05T03:11:11.751855+00:00"}