{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G4EBJ653SA6NPLOZEDIYJPBKGZ","short_pith_number":"pith:G4EBJ653","canonical_record":{"source":{"id":"2107.06405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T21:39:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c678077e97695f4fb8fafbb265bb3985b239457533533abd644421cba5513719","abstract_canon_sha256":"5f9565019769c526837ce608f2195be1b333cca0f2dbbfc93b61ca529f76e8eb"},"schema_version":"1.0"},"canonical_sha256":"370814fbbb903cd7add920d184bc2a367e0ec72a06a12c92307e419918ee09bc","source":{"kind":"arxiv","id":"2107.06405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06405","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06405v1","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06405","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_12","alias_value":"G4EBJ653SA6N","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_16","alias_value":"G4EBJ653SA6NPLOZ","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_8","alias_value":"G4EBJ653","created_at":"2026-07-05T02:57:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G4EBJ653SA6NPLOZEDIYJPBKGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2107.06405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T21:39:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c678077e97695f4fb8fafbb265bb3985b239457533533abd644421cba5513719","abstract_canon_sha256":"5f9565019769c526837ce608f2195be1b333cca0f2dbbfc93b61ca529f76e8eb"},"schema_version":"1.0"},"canonical_sha256":"370814fbbb903cd7add920d184bc2a367e0ec72a06a12c92307e419918ee09bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:57.780275Z","signature_b64":"NytuFBkSqHPVEnudrbZWtfJSFlW1IlHozebmYsxP353yQqEw3J4xZaj/3b2gjCNz5zkaw/mArSMJsSRUZgqyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370814fbbb903cd7add920d184bc2a367e0ec72a06a12c92307e419918ee09bc","last_reissued_at":"2026-07-05T02:57:57.779891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:57.779891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.06405","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":"2026-07-05T02:57:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOR4Yn40Ze40iP0MvAY0qlHy0HrJIUd1+RAD9XqzWUXSeQDERf1oAU/8D5J9iChMVzWY4OW3S1ucARi0NjfUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:11:58.781837Z"},"content_sha256":"75330026db0c6e84356614172ba791b7a2f6f17f4764d6f21ceca188b6543125","schema_version":"1.0","event_id":"sha256:75330026db0c6e84356614172ba791b7a2f6f17f4764d6f21ceca188b6543125"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G4EBJ653SA6NPLOZEDIYJPBKGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Harm van Seijen, Honglak Lee, Jongwook Choi, Mehdi Fatemi, Sungryull Sohn, Sungtae Lee","submitted_at":"2021-07-13T21:39:21Z","abstract_excerpt":"We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP constraint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e.g., going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely exclud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06405","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/2107.06405/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":"2026-07-05T02:57:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0D4+HRHuna4yHIWdQjdb11vsNI+DqW8+ddrAqoWwidhqHyNrpBTx3ppPQ4a0d5YwD9u8Q3cNnO31D0EpPcBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:11:58.782203Z"},"content_sha256":"b1b98e7eef76ca797978f827ed4245e78600c0ca3541bbda9c7a13bada001660","schema_version":"1.0","event_id":"sha256:b1b98e7eef76ca797978f827ed4245e78600c0ca3541bbda9c7a13bada001660"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/bundle.json","state_url":"https://pith.science/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/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":"2026-07-06T18:11:58Z","links":{"resolver":"https://pith.science/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ","bundle":"https://pith.science/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/bundle.json","state":"https://pith.science/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4EBJ653SA6NPLOZEDIYJPBKGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G4EBJ653SA6NPLOZEDIYJPBKGZ","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":"5f9565019769c526837ce608f2195be1b333cca0f2dbbfc93b61ca529f76e8eb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T21:39:21Z","title_canon_sha256":"c678077e97695f4fb8fafbb265bb3985b239457533533abd644421cba5513719"},"schema_version":"1.0","source":{"id":"2107.06405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06405","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06405v1","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06405","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_12","alias_value":"G4EBJ653SA6N","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_16","alias_value":"G4EBJ653SA6NPLOZ","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_8","alias_value":"G4EBJ653","created_at":"2026-07-05T02:57:57Z"}],"graph_snapshots":[{"event_id":"sha256:b1b98e7eef76ca797978f827ed4245e78600c0ca3541bbda9c7a13bada001660","target":"graph","created_at":"2026-07-05T02:57:57Z","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/2107.06405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP constraint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e.g., going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely exclud","authors_text":"Harm van Seijen, Honglak Lee, Jongwook Choi, Mehdi Fatemi, Sungryull Sohn, Sungtae Lee","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T21:39:21Z","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06405","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":"sha256:75330026db0c6e84356614172ba791b7a2f6f17f4764d6f21ceca188b6543125","target":"record","created_at":"2026-07-05T02:57:57Z","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":"5f9565019769c526837ce608f2195be1b333cca0f2dbbfc93b61ca529f76e8eb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T21:39:21Z","title_canon_sha256":"c678077e97695f4fb8fafbb265bb3985b239457533533abd644421cba5513719"},"schema_version":"1.0","source":{"id":"2107.06405","kind":"arxiv","version":1}},"canonical_sha256":"370814fbbb903cd7add920d184bc2a367e0ec72a06a12c92307e419918ee09bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"370814fbbb903cd7add920d184bc2a367e0ec72a06a12c92307e419918ee09bc","first_computed_at":"2026-07-05T02:57:57.779891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:57.779891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NytuFBkSqHPVEnudrbZWtfJSFlW1IlHozebmYsxP353yQqEw3J4xZaj/3b2gjCNz5zkaw/mArSMJsSRUZgqyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:57.780275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75330026db0c6e84356614172ba791b7a2f6f17f4764d6f21ceca188b6543125","sha256:b1b98e7eef76ca797978f827ed4245e78600c0ca3541bbda9c7a13bada001660"],"state_sha256":"5239399c3a5b62d26ec1ba3120b834fab85b1c525f8babd601a3d3d4abcdc9ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JubvAmeBYvFfhl4DWWvwXMt9PT0n4t0BJYW3YQzY2bdlX53pRkKSQy7AbK2fzkDvh/QJ55PUIdwC8kHj82WQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:11:58.784104Z","bundle_sha256":"023836512518c0c9960d01109c24a30d3e66b22a85fefc0f232cdedbb9f37736"}}