{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WOWQ5LRXM6CJ3ZII3KSHSLKN7Q","short_pith_number":"pith:WOWQ5LRX","schema_version":"1.0","canonical_sha256":"b3ad0eae3767849de508daa4792d4dfc1295d6b6cae44eddece17a2efda463b9","source":{"kind":"arxiv","id":"1807.02078","version":1},"attestation_state":"computed","paper":{"title":"Goal-oriented Trajectories for Efficient Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Pardo, Petar Kormushev, Vitaly Levdik","submitted_at":"2018-07-05T16:31:21Z","abstract_excerpt":"Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace single random action choices by random goals selection followed by several steps in their direction. This approach is compatible with any curiosity-based exploration and off-policy reinforcement learning agents and generates longer and safer trajectories than individual random actions"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.02078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-05T16:31:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"472b85bfa7f4eab533786f3271c95ec290e166df3fc0581b2588a2910e92ff1d","abstract_canon_sha256":"cc9335444e0cd333fd313b77f53a13db46355d678bc240ecc8d146d9f8ca1295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:24.304977Z","signature_b64":"Gz4wgRE7RMtC+jC+w5DL+MCOqOKlavUqdQwvh833f8X3LZSi42o+Qc64MVW7zWWRYiHUesuNfSnqNQzM+4sSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ad0eae3767849de508daa4792d4dfc1295d6b6cae44eddece17a2efda463b9","last_reissued_at":"2026-05-18T00:11:24.304610Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:24.304610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal-oriented Trajectories for Efficient Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Pardo, Petar Kormushev, Vitaly Levdik","submitted_at":"2018-07-05T16:31:21Z","abstract_excerpt":"Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace single random action choices by random goals selection followed by several steps in their direction. This approach is compatible with any curiosity-based exploration and off-policy reinforcement learning agents and generates longer and safer trajectories than individual random actions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02078","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.02078","created_at":"2026-05-18T00:11:24.304664+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02078v1","created_at":"2026-05-18T00:11:24.304664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02078","created_at":"2026-05-18T00:11:24.304664+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOWQ5LRXM6CJ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOWQ5LRXM6CJ3ZII","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOWQ5LRX","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q","json":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q.json","graph_json":"https://pith.science/api/pith-number/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/graph.json","events_json":"https://pith.science/api/pith-number/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/events.json","paper":"https://pith.science/paper/WOWQ5LRX"},"agent_actions":{"view_html":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q","download_json":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q.json","view_paper":"https://pith.science/paper/WOWQ5LRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02078&json=true","fetch_graph":"https://pith.science/api/pith-number/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/action/storage_attestation","attest_author":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/action/author_attestation","sign_citation":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/action/citation_signature","submit_replication":"https://pith.science/pith/WOWQ5LRXM6CJ3ZII3KSHSLKN7Q/action/replication_record"}},"created_at":"2026-05-18T00:11:24.304664+00:00","updated_at":"2026-05-18T00:11:24.304664+00:00"}