{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SW5MGJT3VBK23XFTBHBXRB3QQZ","short_pith_number":"pith:SW5MGJT3","schema_version":"1.0","canonical_sha256":"95bac3267ba855addcb309c3788770864cffa33e43ec31f1c1923162e4b5e918","source":{"kind":"arxiv","id":"2011.06764","version":2},"attestation_state":"computed","paper":{"title":"Scaffolding Reflection in Reinforcement Learning Framework for Confinement Escape Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Nishant Mohanty, Suresh Sundaram","submitted_at":"2020-11-13T05:19:22Z","abstract_excerpt":"In this paper, a novel Scaffolding Reflection in Reinforcement Learning (SR2L) is proposed for solving the confinement escape problem (CEP). In CEP, an evader's objective is to attempt escaping a confinement region patrolled by multiple pursuers. Meanwhile, the pursuers aim to reach and capture the evader. The inverse solution for pursuers to try and capture has been extensively studied in the literature. However, the problem of evaders escaping from the region is still an open issue. The SR2L employs an actor-critic framework to enable the evader to escape the confinement region. A time-varyi"},"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":"2011.06764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-13T05:19:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99a7cebaf79ae3c4bceea307b37226eb03db16667575f2426a6871df161010d2","abstract_canon_sha256":"e42e4d507fb36acacccd7904160d0f106f7b779f06cc835aeea08df8e671ff33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:47.347640Z","signature_b64":"3HIbTt5OsuR1ieui8fc4A78PixX/iZ9Akao/enwdZXkKxUjR9Lw/ngfaD0+zcW5tsa7/baBgFMAqNodRcw4tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95bac3267ba855addcb309c3788770864cffa33e43ec31f1c1923162e4b5e918","last_reissued_at":"2026-07-05T02:32:47.347003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:47.347003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaffolding Reflection in Reinforcement Learning Framework for Confinement Escape Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Nishant Mohanty, Suresh Sundaram","submitted_at":"2020-11-13T05:19:22Z","abstract_excerpt":"In this paper, a novel Scaffolding Reflection in Reinforcement Learning (SR2L) is proposed for solving the confinement escape problem (CEP). In CEP, an evader's objective is to attempt escaping a confinement region patrolled by multiple pursuers. Meanwhile, the pursuers aim to reach and capture the evader. The inverse solution for pursuers to try and capture has been extensively studied in the literature. However, the problem of evaders escaping from the region is still an open issue. The SR2L employs an actor-critic framework to enable the evader to escape the confinement region. A time-varyi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06764","kind":"arxiv","version":2},"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/2011.06764/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.06764","created_at":"2026-07-05T02:32:47.347100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06764v2","created_at":"2026-07-05T02:32:47.347100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06764","created_at":"2026-07-05T02:32:47.347100+00:00"},{"alias_kind":"pith_short_12","alias_value":"SW5MGJT3VBK2","created_at":"2026-07-05T02:32:47.347100+00:00"},{"alias_kind":"pith_short_16","alias_value":"SW5MGJT3VBK23XFT","created_at":"2026-07-05T02:32:47.347100+00:00"},{"alias_kind":"pith_short_8","alias_value":"SW5MGJT3","created_at":"2026-07-05T02:32:47.347100+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/SW5MGJT3VBK23XFTBHBXRB3QQZ","json":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ.json","graph_json":"https://pith.science/api/pith-number/SW5MGJT3VBK23XFTBHBXRB3QQZ/graph.json","events_json":"https://pith.science/api/pith-number/SW5MGJT3VBK23XFTBHBXRB3QQZ/events.json","paper":"https://pith.science/paper/SW5MGJT3"},"agent_actions":{"view_html":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ","download_json":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ.json","view_paper":"https://pith.science/paper/SW5MGJT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06764&json=true","fetch_graph":"https://pith.science/api/pith-number/SW5MGJT3VBK23XFTBHBXRB3QQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SW5MGJT3VBK23XFTBHBXRB3QQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ/action/storage_attestation","attest_author":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ/action/author_attestation","sign_citation":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ/action/citation_signature","submit_replication":"https://pith.science/pith/SW5MGJT3VBK23XFTBHBXRB3QQZ/action/replication_record"}},"created_at":"2026-07-05T02:32:47.347100+00:00","updated_at":"2026-07-05T02:32:47.347100+00:00"}