{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RHT7E6GYUG3WYI4TZUTP7V6PQD","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":"b36c55c3a5e87ab875508be45813c8329afa070029f5df2b6b8c81576533460a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-06T16:47:56Z","title_canon_sha256":"d982fd7f21f362e198819d9331869b99d0ddf60f0491e788eb831156891623b3"},"schema_version":"1.0","source":{"id":"2007.02879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02879","created_at":"2026-07-05T01:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02879v1","created_at":"2026-07-05T01:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02879","created_at":"2026-07-05T01:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"RHT7E6GYUG3W","created_at":"2026-07-05T01:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"RHT7E6GYUG3WYI4T","created_at":"2026-07-05T01:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"RHT7E6GY","created_at":"2026-07-05T01:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:68617b0af1d47fd153ef976a08a09800f22098ec54bc7c2aff03849f41cdc45b","target":"graph","created_at":"2026-07-05T01:16:35Z","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/2007.02879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard RL algorithms assume fixed environment dynamics and require a significant amount of interaction to adapt to new environments. We introduce Policy-Dynamics Value Functions (PD-VF), a novel approach for rapidly adapting to dynamics different from those previously seen in training. PD-VF explicitly estimates the cumulative reward in a space of policies and environments. An ensemble of conventional RL policies is used to gather experience on training environments, from which embeddings of both policies and environments can be learned. Then, a value function conditioned on both embeddings ","authors_text":"Arthur Szlam, Max Goldstein, Roberta Raileanu, Rob Fergus","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-06T16:47:56Z","title":"Fast Adaptation via Policy-Dynamics Value Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02879","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":"sha256:6c974049ecbe00b0eb3095f6d7e465faabef4891a3cba566c47ff1cc965ee571","target":"record","created_at":"2026-07-05T01:16:35Z","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":"b36c55c3a5e87ab875508be45813c8329afa070029f5df2b6b8c81576533460a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-06T16:47:56Z","title_canon_sha256":"d982fd7f21f362e198819d9331869b99d0ddf60f0491e788eb831156891623b3"},"schema_version":"1.0","source":{"id":"2007.02879","kind":"arxiv","version":1}},"canonical_sha256":"89e7f278d8a1b76c2393cd26ffd7cf80da6c6d283f7fb945cf7599d1206c98eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89e7f278d8a1b76c2393cd26ffd7cf80da6c6d283f7fb945cf7599d1206c98eb","first_computed_at":"2026-07-05T01:16:35.599495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:35.599495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/P/3bWHFAjdbtmg2ggcSUhukyN2if6VytMSGz2syle7509ZuZU83n7zQPWwPV0fNotnLTl77PmkFLavjeqRzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:35.599968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.02879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c974049ecbe00b0eb3095f6d7e465faabef4891a3cba566c47ff1cc965ee571","sha256:68617b0af1d47fd153ef976a08a09800f22098ec54bc7c2aff03849f41cdc45b"],"state_sha256":"d173420e090cdbf412b2299579efe04cac05a8976ce6715690fb620d08b1b238"}