{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2Q6AJXN5LOHE2XXD6ZI2ZOPMVG","short_pith_number":"pith:2Q6AJXN5","canonical_record":{"source":{"id":"2006.11485","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T03:34:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bc306130484e8f337f9ce05ad5eeece28857356573fb6eb40ac4eee1d5dca9b6","abstract_canon_sha256":"efc1b797dfc0052ca72676a5119f9530b5e9c8733803d4e23d1ee4521ecc5804"},"schema_version":"1.0"},"canonical_sha256":"d43c04ddbd5b8e4d5ee3f651acb9eca9aab529b2b0436cd1f2c3a3daba913b16","source":{"kind":"arxiv","id":"2006.11485","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11485","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11485v4","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11485","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"2Q6AJXN5LOHE","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"2Q6AJXN5LOHE2XXD","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"2Q6AJXN5","created_at":"2026-07-05T02:24:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2Q6AJXN5LOHE2XXD6ZI2ZOPMVG","target":"record","payload":{"canonical_record":{"source":{"id":"2006.11485","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T03:34:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bc306130484e8f337f9ce05ad5eeece28857356573fb6eb40ac4eee1d5dca9b6","abstract_canon_sha256":"efc1b797dfc0052ca72676a5119f9530b5e9c8733803d4e23d1ee4521ecc5804"},"schema_version":"1.0"},"canonical_sha256":"d43c04ddbd5b8e4d5ee3f651acb9eca9aab529b2b0436cd1f2c3a3daba913b16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:10.021593Z","signature_b64":"Ijh+3xV9BPqbCZRqDFRzyEcZBQVa10a5gY2OgIIjPeZXUhzLILUg5mk8NoVnbYlQQ5Za6OXEMBAkUcFcG8UiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43c04ddbd5b8e4d5ee3f651acb9eca9aab529b2b0436cd1f2c3a3daba913b16","last_reissued_at":"2026-07-05T02:24:10.021162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:10.021162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.11485","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":"2026-07-05T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fq3QN0QuNJ5G+ufd+iAZMhf4ZkJxjxQ9loy93OlceYhTx+U6OTV8MvHAmXXPHbJCctHyNdsFgirgHusmPy5tCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:13:13.718023Z"},"content_sha256":"40b9a90fed941bf7591f04b94ea28fc61ec9ab0273c67664e6a3b0bf1d4f4652","schema_version":"1.0","event_id":"sha256:40b9a90fed941bf7591f04b94ea28fc61ec9ab0273c67664e6a3b0bf1d4f4652"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2Q6AJXN5LOHE2XXD6ZI2ZOPMVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Feng Chen, Shangqi Guo, Tianren Zhang, Tian Tan, Xiaolin Hu","submitted_at":"2020-06-20T03:34:45Z","abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space poses difficulties for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11485","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/2006.11485/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":"2026-07-05T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fj0Gm7HSdgVXTsZaYpdJOx49fg5aEYGAWttUnzf8v8Kg+AxD/TAeyB9srnoauDEylk40E5EwSKIeortCeNVHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:13:13.718476Z"},"content_sha256":"35917eff714bbe6d92e1986c62b31e8a34579e560bc656ac619fadc53d32cf93","schema_version":"1.0","event_id":"sha256:35917eff714bbe6d92e1986c62b31e8a34579e560bc656ac619fadc53d32cf93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/bundle.json","state_url":"https://pith.science/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/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":"2026-08-18T04:13:13Z","links":{"resolver":"https://pith.science/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG","bundle":"https://pith.science/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/bundle.json","state":"https://pith.science/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q6AJXN5LOHE2XXD6ZI2ZOPMVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2Q6AJXN5LOHE2XXD6ZI2ZOPMVG","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":"efc1b797dfc0052ca72676a5119f9530b5e9c8733803d4e23d1ee4521ecc5804","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T03:34:45Z","title_canon_sha256":"bc306130484e8f337f9ce05ad5eeece28857356573fb6eb40ac4eee1d5dca9b6"},"schema_version":"1.0","source":{"id":"2006.11485","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11485","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11485v4","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11485","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"2Q6AJXN5LOHE","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"2Q6AJXN5LOHE2XXD","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"2Q6AJXN5","created_at":"2026-07-05T02:24:10Z"}],"graph_snapshots":[{"event_id":"sha256:35917eff714bbe6d92e1986c62b31e8a34579e560bc656ac619fadc53d32cf93","target":"graph","created_at":"2026-07-05T02:24:10Z","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/2006.11485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space poses difficulties for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency c","authors_text":"Feng Chen, Shangqi Guo, Tianren Zhang, Tian Tan, Xiaolin Hu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T03:34:45Z","title":"Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11485","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":"sha256:40b9a90fed941bf7591f04b94ea28fc61ec9ab0273c67664e6a3b0bf1d4f4652","target":"record","created_at":"2026-07-05T02:24:10Z","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":"efc1b797dfc0052ca72676a5119f9530b5e9c8733803d4e23d1ee4521ecc5804","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T03:34:45Z","title_canon_sha256":"bc306130484e8f337f9ce05ad5eeece28857356573fb6eb40ac4eee1d5dca9b6"},"schema_version":"1.0","source":{"id":"2006.11485","kind":"arxiv","version":4}},"canonical_sha256":"d43c04ddbd5b8e4d5ee3f651acb9eca9aab529b2b0436cd1f2c3a3daba913b16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43c04ddbd5b8e4d5ee3f651acb9eca9aab529b2b0436cd1f2c3a3daba913b16","first_computed_at":"2026-07-05T02:24:10.021162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:10.021162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ijh+3xV9BPqbCZRqDFRzyEcZBQVa10a5gY2OgIIjPeZXUhzLILUg5mk8NoVnbYlQQ5Za6OXEMBAkUcFcG8UiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:10.021593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11485","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b9a90fed941bf7591f04b94ea28fc61ec9ab0273c67664e6a3b0bf1d4f4652","sha256:35917eff714bbe6d92e1986c62b31e8a34579e560bc656ac619fadc53d32cf93"],"state_sha256":"c4a937513c625551aa87cdfee6319f755e43b7333c49cf155a21d7df86da5916"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dna3VBNHy7Zppgrq1OJETJpB8buIPsjtBoxjZZ6e/3Cwv+0g7yIXzi26KuzGxrwuZlXA0IDO4W1UWFV3TTOGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:13:13.721908Z","bundle_sha256":"7d47254f291c4e5ab45a3f82ac83733cdc80313fd648045e148a513696077064"}}