{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XCNXVJNBTBTF4ADJSMVCECAHAN","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":"cc97e3872118f8b32f173b846f22f8aac4ed99ce976e4541772899a1da4ad1f5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:26:54Z","title_canon_sha256":"1e1617a43febb3892a6098fc66e3f3f831a14c6be418ed763e4b7a6b456adb70"},"schema_version":"1.0","source":{"id":"2012.08621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08621","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08621v1","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08621","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"XCNXVJNBTBTF","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"XCNXVJNBTBTF4ADJ","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"XCNXVJNB","created_at":"2026-07-05T02:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:f31054ee1b3b73c0f8db4d0dfd8ee811f4d1ab6a18b31710aad784c6dbd56174","target":"graph","created_at":"2026-07-05T02:00:01Z","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/2012.08621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient exploration under sparse rewards remains a key challenge in deep reinforcement learning. To guide exploration, previous work makes extensive use of intrinsic reward (IR). There are many heuristics for IR, including visitation counts, curiosity, and state-difference. In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR. The criterion helps the agent explore Beyond the Boundary of explored regions and mitigates common issues in count-based methods, such as short-sightednes","authors_text":"Huazhe Xu, Joseph E. Gonzalez, Kurt Keutzer, Tianjun Zhang, Xiaolong Wang, Yi Wu, Yuandong Tian","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:26:54Z","title":"BeBold: Exploration Beyond the Boundary of Explored Regions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08621","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:beb0d92d66b8a299f1c029516a7e3ed2499064fb7736ebb23eb09345f6a0f88e","target":"record","created_at":"2026-07-05T02:00:01Z","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":"cc97e3872118f8b32f173b846f22f8aac4ed99ce976e4541772899a1da4ad1f5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:26:54Z","title_canon_sha256":"1e1617a43febb3892a6098fc66e3f3f831a14c6be418ed763e4b7a6b456adb70"},"schema_version":"1.0","source":{"id":"2012.08621","kind":"arxiv","version":1}},"canonical_sha256":"b89b7aa5a198665e0069932a220807036b842460a61e124ec23416ac76dd53ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b89b7aa5a198665e0069932a220807036b842460a61e124ec23416ac76dd53ce","first_computed_at":"2026-07-05T02:00:01.372756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:01.372756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iJlESWume+u9TBBQmQxh/QD9YeZs9E7MAFBcB9Bp2/8u2c63RCN1PwDwg2jrUzYeKCsAIBH372x/xPn6ZFRXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:01.373218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beb0d92d66b8a299f1c029516a7e3ed2499064fb7736ebb23eb09345f6a0f88e","sha256:f31054ee1b3b73c0f8db4d0dfd8ee811f4d1ab6a18b31710aad784c6dbd56174"],"state_sha256":"c9ab798ca64a81bc865106c320f8d6173d4e1c27776e6c17d54ad849a46f5981"}