{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BRALV2KRVVFSCN4S6U3CF3PIUX","short_pith_number":"pith:BRALV2KR","canonical_record":{"source":{"id":"2106.10075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T11:51:49Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d18cb4b470e275f962758089aa0fd7a2df345f009d0b37c0b5e2b6778ea624b1","abstract_canon_sha256":"2b72bbc0ec276e9ff8682eb8605e822df9250454348d11fd7cecc87663765885"},"schema_version":"1.0"},"canonical_sha256":"0c40bae951ad4b213792f53622ede8a5d6c6d17aa952d005ba00d2faa0ab2ee5","source":{"kind":"arxiv","id":"2106.10075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10075","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10075v1","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10075","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"BRALV2KRVVFS","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_16","alias_value":"BRALV2KRVVFSCN4S","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_8","alias_value":"BRALV2KR","created_at":"2026-07-05T02:50:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BRALV2KRVVFSCN4S6U3CF3PIUX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.10075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T11:51:49Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d18cb4b470e275f962758089aa0fd7a2df345f009d0b37c0b5e2b6778ea624b1","abstract_canon_sha256":"2b72bbc0ec276e9ff8682eb8605e822df9250454348d11fd7cecc87663765885"},"schema_version":"1.0"},"canonical_sha256":"0c40bae951ad4b213792f53622ede8a5d6c6d17aa952d005ba00d2faa0ab2ee5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:33.153660Z","signature_b64":"gDMHSS/5aEuEDbXl1NS+egSyqBtgdXB7vYlQtQzrnjhdNBGBHUck32vITyzxTetxf1BWAKXspk87Ct3mQHqeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c40bae951ad4b213792f53622ede8a5d6c6d17aa952d005ba00d2faa0ab2ee5","last_reissued_at":"2026-07-05T02:50:33.153238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:33.153238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.10075","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFppllBx0ga3zDyHx4l9MFOkkWgpjsuMyjTk+Gtt75rFx0hHkvD0S3ERzUUvRQ1WApIkNzy3CxOCWVjqdgQXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:04:50.482451Z"},"content_sha256":"c2668d403da78437fbdac6e7a6f378b714f4a35a0750a6b6fbde6f3d60ecf213","schema_version":"1.0","event_id":"sha256:c2668d403da78437fbdac6e7a6f378b714f4a35a0750a6b6fbde6f3d60ecf213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BRALV2KRVVFSCN4S6U3CF3PIUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Plan via a Multi-Step Policy Regression Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Michael Janschek, Stefan Harmeling, Stefan Wagner, Tobias Uelwer","submitted_at":"2021-06-18T11:51:49Z","abstract_excerpt":"We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved. This is for example the case for maze environments where ideally an optimal path is determined. Instead of learning a policy for a single step, we want to learn a policy that can predict n actions in advance. Our proposed method called policy horizon regression (PHR) uses knowledge of the environment sampled by A2C to learn an n dimensional policy vector in a policy distillation setup which yields n sequential actions per observation. We test our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10075","kind":"arxiv","version":1},"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/2106.10075/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":"2026-07-05T02:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84JYzjBHG2XRVEf/dAZ5nm1rvkBedNE1jwp/8U/OI9BE2tZr8s7iOLw73eh7ULBdsc9e16TiAYDHXJ4he9x3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:04:50.482844Z"},"content_sha256":"63d76b5cf230a840ed1bba91b54030f87894c427a1b643e5f943fa061fea94b2","schema_version":"1.0","event_id":"sha256:63d76b5cf230a840ed1bba91b54030f87894c427a1b643e5f943fa061fea94b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/bundle.json","state_url":"https://pith.science/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/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":"2026-07-11T20:04:50Z","links":{"resolver":"https://pith.science/pith/BRALV2KRVVFSCN4S6U3CF3PIUX","bundle":"https://pith.science/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/bundle.json","state":"https://pith.science/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BRALV2KRVVFSCN4S6U3CF3PIUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BRALV2KRVVFSCN4S6U3CF3PIUX","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":"2b72bbc0ec276e9ff8682eb8605e822df9250454348d11fd7cecc87663765885","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T11:51:49Z","title_canon_sha256":"d18cb4b470e275f962758089aa0fd7a2df345f009d0b37c0b5e2b6778ea624b1"},"schema_version":"1.0","source":{"id":"2106.10075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10075","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10075v1","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10075","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"BRALV2KRVVFS","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_16","alias_value":"BRALV2KRVVFSCN4S","created_at":"2026-07-05T02:50:33Z"},{"alias_kind":"pith_short_8","alias_value":"BRALV2KR","created_at":"2026-07-05T02:50:33Z"}],"graph_snapshots":[{"event_id":"sha256:63d76b5cf230a840ed1bba91b54030f87894c427a1b643e5f943fa061fea94b2","target":"graph","created_at":"2026-07-05T02:50:33Z","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/2106.10075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved. This is for example the case for maze environments where ideally an optimal path is determined. Instead of learning a policy for a single step, we want to learn a policy that can predict n actions in advance. Our proposed method called policy horizon regression (PHR) uses knowledge of the environment sampled by A2C to learn an n dimensional policy vector in a policy distillation setup which yields n sequential actions per observation. We test our method","authors_text":"Michael Janschek, Stefan Harmeling, Stefan Wagner, Tobias Uelwer","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T11:51:49Z","title":"Learning to Plan via a Multi-Step Policy Regression Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10075","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:c2668d403da78437fbdac6e7a6f378b714f4a35a0750a6b6fbde6f3d60ecf213","target":"record","created_at":"2026-07-05T02:50:33Z","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":"2b72bbc0ec276e9ff8682eb8605e822df9250454348d11fd7cecc87663765885","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T11:51:49Z","title_canon_sha256":"d18cb4b470e275f962758089aa0fd7a2df345f009d0b37c0b5e2b6778ea624b1"},"schema_version":"1.0","source":{"id":"2106.10075","kind":"arxiv","version":1}},"canonical_sha256":"0c40bae951ad4b213792f53622ede8a5d6c6d17aa952d005ba00d2faa0ab2ee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c40bae951ad4b213792f53622ede8a5d6c6d17aa952d005ba00d2faa0ab2ee5","first_computed_at":"2026-07-05T02:50:33.153238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:33.153238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gDMHSS/5aEuEDbXl1NS+egSyqBtgdXB7vYlQtQzrnjhdNBGBHUck32vITyzxTetxf1BWAKXspk87Ct3mQHqeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:33.153660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2668d403da78437fbdac6e7a6f378b714f4a35a0750a6b6fbde6f3d60ecf213","sha256:63d76b5cf230a840ed1bba91b54030f87894c427a1b643e5f943fa061fea94b2"],"state_sha256":"927c6edede9f441307882a93c020c9e2f3b6af94fd5c8fa45dccada8de690315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ObgLGgtVEPvedHh1twn1SBPily8eivRcR9RwTrhG9ww+gfE22k1VMbza9fSIpIktr8YBYSZGiu9M/4qha2WaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T20:04:50.484934Z","bundle_sha256":"3a3465c62f7ef3a5da8f0f0aaec983e1307c419ad3134e583cef7d952201c535"}}