{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TXASHBIKQMXMTFHAFW22LW4IEA","short_pith_number":"pith:TXASHBIK","canonical_record":{"source":{"id":"2205.11357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T14:42:38Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"27bbbc3992b234f69b5781a1af744d174819c1944f501dc9a6a5dda207a929bb","abstract_canon_sha256":"5ae85ac12789ee4f9ffb9e61229005eee387e8fd95e20bce0283bd0c5cd95139"},"schema_version":"1.0"},"canonical_sha256":"9dc123850a832ec994e02db5a5db8820142f9f81a3cffd00600d07ccac610e25","source":{"kind":"arxiv","id":"2205.11357","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11357","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11357v3","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11357","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"TXASHBIKQMXM","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_16","alias_value":"TXASHBIKQMXMTFHA","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_8","alias_value":"TXASHBIK","created_at":"2026-07-05T07:24:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TXASHBIKQMXMTFHAFW22LW4IEA","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T14:42:38Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"27bbbc3992b234f69b5781a1af744d174819c1944f501dc9a6a5dda207a929bb","abstract_canon_sha256":"5ae85ac12789ee4f9ffb9e61229005eee387e8fd95e20bce0283bd0c5cd95139"},"schema_version":"1.0"},"canonical_sha256":"9dc123850a832ec994e02db5a5db8820142f9f81a3cffd00600d07ccac610e25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:46.030840Z","signature_b64":"tTKeIWu/+hxrgaFlXoTfg3d6E9l5UEMVaFb8PPqCeeiSOWrb3YUISWAaTMBmyqCciRrC9QHxGylRfnnqCAjbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dc123850a832ec994e02db5a5db8820142f9f81a3cffd00600d07ccac610e25","last_reissued_at":"2026-07-05T07:24:46.030385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:46.030385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11357","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CG7ZpavofdU0JpPJN3TRJB+DX2xQwRhHmXrRMDjArNNWobEXUcaLxWS88fELc6Oegk5l8HaycdXLENukpSNWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:46:14.339627Z"},"content_sha256":"5ca203d78fb7cd8bc859a9ab4d3a67e3e993788656865ace22c84b0f09189a9b","schema_version":"1.0","event_id":"sha256:5ca203d78fb7cd8bc859a9ab4d3a67e3e993788656865ace22c84b0f09189a9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TXASHBIKQMXMTFHAFW22LW4IEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bodo Rosenhahn, Carolin Benjamins, Frederik Schubert, Marius Lindauer, Sebastian D\\\"ohler","submitted_at":"2022-05-23T14:42:38Z","abstract_excerpt":"The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is improved. Although agents initialized with such a prior policy can achieve a significantly higher reward with fewer samples when finetuned on the downstream task, it is still an open question how an optimal pretrained prior policy can be achieved in practice. In this work, we present POLTER (Policy Trajectory Ensemble Regularization) - a general method to regularize the pretraining that can be applied to any URL algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11357","kind":"arxiv","version":3},"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/2205.11357/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CwGjFZGfy3Ahei+eOPjHCqz5yf4d2sWS4JpDWotTr/gfZY2+QRi26YcAz+d++AQZLjW5G9PKz9hcoIzmrzpFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:46:14.340270Z"},"content_sha256":"0d175b7e5b1a8091050133edf1e8ecb0c7966a6620ae1391a0faaeb6aefedf76","schema_version":"1.0","event_id":"sha256:0d175b7e5b1a8091050133edf1e8ecb0c7966a6620ae1391a0faaeb6aefedf76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXASHBIKQMXMTFHAFW22LW4IEA/bundle.json","state_url":"https://pith.science/pith/TXASHBIKQMXMTFHAFW22LW4IEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXASHBIKQMXMTFHAFW22LW4IEA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T16:46:14Z","links":{"resolver":"https://pith.science/pith/TXASHBIKQMXMTFHAFW22LW4IEA","bundle":"https://pith.science/pith/TXASHBIKQMXMTFHAFW22LW4IEA/bundle.json","state":"https://pith.science/pith/TXASHBIKQMXMTFHAFW22LW4IEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXASHBIKQMXMTFHAFW22LW4IEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TXASHBIKQMXMTFHAFW22LW4IEA","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":"5ae85ac12789ee4f9ffb9e61229005eee387e8fd95e20bce0283bd0c5cd95139","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T14:42:38Z","title_canon_sha256":"27bbbc3992b234f69b5781a1af744d174819c1944f501dc9a6a5dda207a929bb"},"schema_version":"1.0","source":{"id":"2205.11357","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11357","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11357v3","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11357","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"TXASHBIKQMXM","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_16","alias_value":"TXASHBIKQMXMTFHA","created_at":"2026-07-05T07:24:46Z"},{"alias_kind":"pith_short_8","alias_value":"TXASHBIK","created_at":"2026-07-05T07:24:46Z"}],"graph_snapshots":[{"event_id":"sha256:0d175b7e5b1a8091050133edf1e8ecb0c7966a6620ae1391a0faaeb6aefedf76","target":"graph","created_at":"2026-07-05T07:24:46Z","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/2205.11357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is improved. Although agents initialized with such a prior policy can achieve a significantly higher reward with fewer samples when finetuned on the downstream task, it is still an open question how an optimal pretrained prior policy can be achieved in practice. In this work, we present POLTER (Policy Trajectory Ensemble Regularization) - a general method to regularize the pretraining that can be applied to any URL algo","authors_text":"Bodo Rosenhahn, Carolin Benjamins, Frederik Schubert, Marius Lindauer, Sebastian D\\\"ohler","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T14:42:38Z","title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11357","kind":"arxiv","version":3},"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":"sha256:5ca203d78fb7cd8bc859a9ab4d3a67e3e993788656865ace22c84b0f09189a9b","target":"record","created_at":"2026-07-05T07:24:46Z","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":"5ae85ac12789ee4f9ffb9e61229005eee387e8fd95e20bce0283bd0c5cd95139","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T14:42:38Z","title_canon_sha256":"27bbbc3992b234f69b5781a1af744d174819c1944f501dc9a6a5dda207a929bb"},"schema_version":"1.0","source":{"id":"2205.11357","kind":"arxiv","version":3}},"canonical_sha256":"9dc123850a832ec994e02db5a5db8820142f9f81a3cffd00600d07ccac610e25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dc123850a832ec994e02db5a5db8820142f9f81a3cffd00600d07ccac610e25","first_computed_at":"2026-07-05T07:24:46.030385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:46.030385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTKeIWu/+hxrgaFlXoTfg3d6E9l5UEMVaFb8PPqCeeiSOWrb3YUISWAaTMBmyqCciRrC9QHxGylRfnnqCAjbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:46.030840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11357","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ca203d78fb7cd8bc859a9ab4d3a67e3e993788656865ace22c84b0f09189a9b","sha256:0d175b7e5b1a8091050133edf1e8ecb0c7966a6620ae1391a0faaeb6aefedf76"],"state_sha256":"733f11818b20a413fa380f11559aa078c2032a45a242b23acdedc4f8749b8856"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9HK8J82pQ+LWMgqtsieWrS01diNp+UNBPwBKXjqKkT/g0B7LChWej0BJGuniRNJulfbBvNABC4Gd1hwbXa8rDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:46:14.345342Z","bundle_sha256":"82deb7f3999e3115afe5d9487ded3bce09ce34dff1e140ae943caeb142c7f1fe"}}