{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XVME4CDOC3XOOXZ3LPGIZPKUT2","short_pith_number":"pith:XVME4CDO","canonical_record":{"source":{"id":"2108.05872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-12T17:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"4e761ace012ea7e57f6dd17b23ddc733d4f3cd42be00b7f289878828e1ac6da4","abstract_canon_sha256":"974f0cb7b3ea0603e9ccc5aa16f98bcd7c82d9a2dcd846d0ee400c07f7832cd0"},"schema_version":"1.0"},"canonical_sha256":"bd584e086e16eee75f3b5bcc8cbd549eb160c05a126f7388dcaf15bee7511702","source":{"kind":"arxiv","id":"2108.05872","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05872","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05872v1","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05872","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"XVME4CDOC3XO","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"XVME4CDOC3XOOXZ3","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"XVME4CDO","created_at":"2026-07-05T03:05:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XVME4CDOC3XOOXZ3LPGIZPKUT2","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-12T17:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"4e761ace012ea7e57f6dd17b23ddc733d4f3cd42be00b7f289878828e1ac6da4","abstract_canon_sha256":"974f0cb7b3ea0603e9ccc5aa16f98bcd7c82d9a2dcd846d0ee400c07f7832cd0"},"schema_version":"1.0"},"canonical_sha256":"bd584e086e16eee75f3b5bcc8cbd549eb160c05a126f7388dcaf15bee7511702","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:23.333964Z","signature_b64":"BWalNgZX4DNTTxMK7HqwGQDaBe8YZ8PMG1CWcmYrXudnsJr/PZLYJh3EWh45/2zBCgfA6beRFjD8WtWlZMw0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd584e086e16eee75f3b5bcc8cbd549eb160c05a126f7388dcaf15bee7511702","last_reissued_at":"2026-07-05T03:05:23.333500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:23.333500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05872","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":"2026-07-05T03:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cioYbYfhNKaDi4Gwstuwc4ATKhdKYHwUZ1Zx+JYs9Il44xX3S3MAHajzVl3n1aBRVMK9VLkk4aRK+tSMgzczDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:55:27.410745Z"},"content_sha256":"c4f1a28c97a07733587bcc7e9364963e2a17b530d7f9df635adf5492990bb173","schema_version":"1.0","event_id":"sha256:c4f1a28c97a07733587bcc7e9364963e2a17b530d7f9df635adf5492990bb173"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XVME4CDOC3XOOXZ3LPGIZPKUT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Levy, George Konidaris, Willie McClinton","submitted_at":"2021-08-12T17:42:12Z","abstract_excerpt":"Sparse rewards and long time horizons remain challenging for reinforcement learning algorithms. Exploration bonuses can help in sparse reward settings by encouraging agents to explore the state space, while hierarchical approaches can assist with long-horizon tasks by decomposing lengthy tasks into shorter subtasks. We propose HAC Explore (HACx), a new method that combines these approaches by integrating the exploration bonus method Random Network Distillation (RND) into the hierarchical approach Hierarchical Actor-Critic (HAC). HACx outperforms either component method on its own, as well as a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05872","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/2108.05872/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":"2026-07-05T03:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Rv8/f1z9nSskfZO4IICTp+jcLq1l8k9qDQ1BBtoigNEiTj3W+uyeGUWAc1+PjTK5uN+QQkWp68Hc0w91WNQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:55:27.411116Z"},"content_sha256":"a12ae5e01fbf9159b46b219c1b6a9cfcc7f950c34d60ab2df36d98ff2526c6cb","schema_version":"1.0","event_id":"sha256:a12ae5e01fbf9159b46b219c1b6a9cfcc7f950c34d60ab2df36d98ff2526c6cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/bundle.json","state_url":"https://pith.science/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/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":"2026-08-05T22:55:27Z","links":{"resolver":"https://pith.science/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2","bundle":"https://pith.science/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/bundle.json","state":"https://pith.science/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVME4CDOC3XOOXZ3LPGIZPKUT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XVME4CDOC3XOOXZ3LPGIZPKUT2","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":"974f0cb7b3ea0603e9ccc5aa16f98bcd7c82d9a2dcd846d0ee400c07f7832cd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-12T17:42:12Z","title_canon_sha256":"4e761ace012ea7e57f6dd17b23ddc733d4f3cd42be00b7f289878828e1ac6da4"},"schema_version":"1.0","source":{"id":"2108.05872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05872","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05872v1","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05872","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"XVME4CDOC3XO","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"XVME4CDOC3XOOXZ3","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"XVME4CDO","created_at":"2026-07-05T03:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:a12ae5e01fbf9159b46b219c1b6a9cfcc7f950c34d60ab2df36d98ff2526c6cb","target":"graph","created_at":"2026-07-05T03:05:23Z","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/2108.05872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse rewards and long time horizons remain challenging for reinforcement learning algorithms. Exploration bonuses can help in sparse reward settings by encouraging agents to explore the state space, while hierarchical approaches can assist with long-horizon tasks by decomposing lengthy tasks into shorter subtasks. We propose HAC Explore (HACx), a new method that combines these approaches by integrating the exploration bonus method Random Network Distillation (RND) into the hierarchical approach Hierarchical Actor-Critic (HAC). HACx outperforms either component method on its own, as well as a","authors_text":"Andrew Levy, George Konidaris, Willie McClinton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-12T17:42:12Z","title":"HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05872","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:c4f1a28c97a07733587bcc7e9364963e2a17b530d7f9df635adf5492990bb173","target":"record","created_at":"2026-07-05T03:05:23Z","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":"974f0cb7b3ea0603e9ccc5aa16f98bcd7c82d9a2dcd846d0ee400c07f7832cd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-12T17:42:12Z","title_canon_sha256":"4e761ace012ea7e57f6dd17b23ddc733d4f3cd42be00b7f289878828e1ac6da4"},"schema_version":"1.0","source":{"id":"2108.05872","kind":"arxiv","version":1}},"canonical_sha256":"bd584e086e16eee75f3b5bcc8cbd549eb160c05a126f7388dcaf15bee7511702","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd584e086e16eee75f3b5bcc8cbd549eb160c05a126f7388dcaf15bee7511702","first_computed_at":"2026-07-05T03:05:23.333500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:23.333500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BWalNgZX4DNTTxMK7HqwGQDaBe8YZ8PMG1CWcmYrXudnsJr/PZLYJh3EWh45/2zBCgfA6beRFjD8WtWlZMw0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:23.333964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4f1a28c97a07733587bcc7e9364963e2a17b530d7f9df635adf5492990bb173","sha256:a12ae5e01fbf9159b46b219c1b6a9cfcc7f950c34d60ab2df36d98ff2526c6cb"],"state_sha256":"e563ff1bb745a9cfd73650eda88b9da6a6090b5184d2f8dfbf237ca252bde58b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9sgBilaDcs6PdKrFaV6G9aO0HwEHaIhREh6T2uxBUB9EvPKYhUmvjRva4J9H2s3PlXeFXTHKO86rp+ijzTJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:55:27.414017Z","bundle_sha256":"be33874642bd042a106c54fcd03eae6eb727c52929f329c8524ae96ccb21289f"}}