{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HA6PXHUVY7ZO4UI4YGAA7NSWSV","short_pith_number":"pith:HA6PXHUV","canonical_record":{"source":{"id":"2410.09536","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:55:26Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8963dafa240035c01782fec9295fcf9598f3f9ec208deb5f4b3c3026d9b2637e","abstract_canon_sha256":"dde41832630b50e94636c2c24658cf432352cc138d80970cb573f6d146678984"},"schema_version":"1.0"},"canonical_sha256":"383cfb9e95c7f2ee511cc1800fb656957a083275792587ad00f1e80ab0fbd620","source":{"kind":"arxiv","id":"2410.09536","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09536","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09536v4","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09536","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_12","alias_value":"HA6PXHUVY7ZO","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_16","alias_value":"HA6PXHUVY7ZO4UI4","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_8","alias_value":"HA6PXHUV","created_at":"2026-07-05T10:31:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HA6PXHUVY7ZO4UI4YGAA7NSWSV","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09536","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:55:26Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8963dafa240035c01782fec9295fcf9598f3f9ec208deb5f4b3c3026d9b2637e","abstract_canon_sha256":"dde41832630b50e94636c2c24658cf432352cc138d80970cb573f6d146678984"},"schema_version":"1.0"},"canonical_sha256":"383cfb9e95c7f2ee511cc1800fb656957a083275792587ad00f1e80ab0fbd620","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:48.484262Z","signature_b64":"9prgnwuJOPc4LyxyBJ4UaRVBDaCdKk4x0x43vRQe+EzY2JchO/Az9VXE+Jtj53oUcfSP7Nb4tMY78CCISFl5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"383cfb9e95c7f2ee511cc1800fb656957a083275792587ad00f1e80ab0fbd620","last_reissued_at":"2026-07-05T10:31:48.483255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:48.483255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09536","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIgnd9izpP8N2rPaSDdcc9w616b+hOrCkBJwcto5ahbxZPlzlmblkQCex0FEO42o4f9KRQ2cWksP8EgOrySnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:56:20.704061Z"},"content_sha256":"2633a54dc35814cfd1e2bf48d5036d3e0df2404433474994cc772d51f3608ffa","schema_version":"1.0","event_id":"sha256:2633a54dc35814cfd1e2bf48d5036d3e0df2404433474994cc772d51f3608ffa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HA6PXHUVY7ZO4UI4YGAA7NSWSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dong Tian, Ge Li, Gerhard Neumann, Hongyi Zhou, Rudolf Lioutikov, Xinkai Jiang","submitted_at":"2024-10-12T13:55:26Z","abstract_excerpt":"This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time steps instead of single actions at every time step. These trajectories are typically parameterized by trajectory generators such as Movement Primitives (MP), allowing for smooth and efficient exploration over long horizons while capturing high-level temporal correlations. However, ERL methods are often constrained to on-policy frameworks due to the difficulty of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09536","kind":"arxiv","version":4},"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/2410.09536/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":"2026-07-05T10:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldsOdwrF67YSMmCGEvd7Vcvljy3wXgStGZVGywwDZqYH3sE5v/G+N6Yp5ksbxUn9cwBs+gPZOkwNIk8pMuH9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:56:20.705064Z"},"content_sha256":"4929996a81816bb06d10802440f91ac94b4dc83ccace4a916f787bddd38c4cd4","schema_version":"1.0","event_id":"sha256:4929996a81816bb06d10802440f91ac94b4dc83ccace4a916f787bddd38c4cd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/bundle.json","state_url":"https://pith.science/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/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":"2026-08-16T16:56:20Z","links":{"resolver":"https://pith.science/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV","bundle":"https://pith.science/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/bundle.json","state":"https://pith.science/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HA6PXHUVY7ZO4UI4YGAA7NSWSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HA6PXHUVY7ZO4UI4YGAA7NSWSV","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":"dde41832630b50e94636c2c24658cf432352cc138d80970cb573f6d146678984","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:55:26Z","title_canon_sha256":"8963dafa240035c01782fec9295fcf9598f3f9ec208deb5f4b3c3026d9b2637e"},"schema_version":"1.0","source":{"id":"2410.09536","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09536","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09536v4","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09536","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_12","alias_value":"HA6PXHUVY7ZO","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_16","alias_value":"HA6PXHUVY7ZO4UI4","created_at":"2026-07-05T10:31:48Z"},{"alias_kind":"pith_short_8","alias_value":"HA6PXHUV","created_at":"2026-07-05T10:31:48Z"}],"graph_snapshots":[{"event_id":"sha256:4929996a81816bb06d10802440f91ac94b4dc83ccace4a916f787bddd38c4cd4","target":"graph","created_at":"2026-07-05T10:31:48Z","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/2410.09536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time steps instead of single actions at every time step. These trajectories are typically parameterized by trajectory generators such as Movement Primitives (MP), allowing for smooth and efficient exploration over long horizons while capturing high-level temporal correlations. However, ERL methods are often constrained to on-policy frameworks due to the difficulty of","authors_text":"Dong Tian, Ge Li, Gerhard Neumann, Hongyi Zhou, Rudolf Lioutikov, Xinkai Jiang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:55:26Z","title":"TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09536","kind":"arxiv","version":4},"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":"sha256:2633a54dc35814cfd1e2bf48d5036d3e0df2404433474994cc772d51f3608ffa","target":"record","created_at":"2026-07-05T10:31:48Z","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":"dde41832630b50e94636c2c24658cf432352cc138d80970cb573f6d146678984","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:55:26Z","title_canon_sha256":"8963dafa240035c01782fec9295fcf9598f3f9ec208deb5f4b3c3026d9b2637e"},"schema_version":"1.0","source":{"id":"2410.09536","kind":"arxiv","version":4}},"canonical_sha256":"383cfb9e95c7f2ee511cc1800fb656957a083275792587ad00f1e80ab0fbd620","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"383cfb9e95c7f2ee511cc1800fb656957a083275792587ad00f1e80ab0fbd620","first_computed_at":"2026-07-05T10:31:48.483255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:48.483255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9prgnwuJOPc4LyxyBJ4UaRVBDaCdKk4x0x43vRQe+EzY2JchO/Az9VXE+Jtj53oUcfSP7Nb4tMY78CCISFl5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:48.484262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09536","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2633a54dc35814cfd1e2bf48d5036d3e0df2404433474994cc772d51f3608ffa","sha256:4929996a81816bb06d10802440f91ac94b4dc83ccace4a916f787bddd38c4cd4"],"state_sha256":"9d18b00ee335466ba7c829c0f55ecab30468ddd81cdd16878582a0f950c12598"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVXURRJ1xuiRqgPP+e3rKaGZ7b9jW0IWBQ/Iby4Ykaq/kfdhf4vLpvhR8h8AgyGXjrbOkJYHUMWUz1ZtXR7oCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T16:56:20.710932Z","bundle_sha256":"18b00743cee65a041ee357655d9bf4a3172ad6b257afb60ed96a5b2e7d470d88"}}