{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LF7SPG6G6HIVTW2ZXRZ5OFHMA7","short_pith_number":"pith:LF7SPG6G","schema_version":"1.0","canonical_sha256":"597f279bc6f1d159db59bc73d714ec07f89679dac0916eeab6c151fdebc91434","source":{"kind":"arxiv","id":"2408.04054","version":2},"attestation_state":"computed","paper":{"title":"PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amisha Bhaskar, Pratap Tokekar, Sachin R Jadhav, Zahiruddin Mahammad","submitted_at":"2024-08-07T19:30:08Z","abstract_excerpt":"Reinforcement Learning (RL) has shown remarkable progress in simulation environments, yet its application to real-world robotic tasks remains limited due to challenges in exploration and generalization. To address these issues, we introduce PLANRL, a framework that chooses when the robot should use classical motion planning and when it should learn a policy. To further improve the efficiency in exploration, we use imitation data to bootstrap the exploration. PLANRL dynamically switches between two modes of operation: reaching a waypoint using classical techniques when away from the objects and"},"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":"2408.04054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-07T19:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"f37ce8af36b42b545fb1cd4bf65a6a40d2dddc6e411f5cbd27ccd90d5c34cce3","abstract_canon_sha256":"7ce2b9cfba035d031ca6442616d70bb70964ba36a2aa65c84a03616a01256883"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:47.641177Z","signature_b64":"mqcH4c4y8m9BzTXg2YJ9YQWwREhVx0eS23heiJnXb9x4J5f8IzjgLjwPz9tX/amSl+eYqI3t4slQrMU0zFrfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"597f279bc6f1d159db59bc73d714ec07f89679dac0916eeab6c151fdebc91434","last_reissued_at":"2026-07-05T09:21:47.640710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:47.640710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amisha Bhaskar, Pratap Tokekar, Sachin R Jadhav, Zahiruddin Mahammad","submitted_at":"2024-08-07T19:30:08Z","abstract_excerpt":"Reinforcement Learning (RL) has shown remarkable progress in simulation environments, yet its application to real-world robotic tasks remains limited due to challenges in exploration and generalization. To address these issues, we introduce PLANRL, a framework that chooses when the robot should use classical motion planning and when it should learn a policy. To further improve the efficiency in exploration, we use imitation data to bootstrap the exploration. PLANRL dynamically switches between two modes of operation: reaching a waypoint using classical techniques when away from the objects and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04054","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/2408.04054/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":"2408.04054","created_at":"2026-07-05T09:21:47.640765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04054v2","created_at":"2026-07-05T09:21:47.640765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04054","created_at":"2026-07-05T09:21:47.640765+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF7SPG6G6HIV","created_at":"2026-07-05T09:21:47.640765+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF7SPG6G6HIVTW2Z","created_at":"2026-07-05T09:21:47.640765+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF7SPG6G","created_at":"2026-07-05T09:21:47.640765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04280","citing_title":"A KL-regularization Framework for Learning to Plan with Adaptive Priors","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7","json":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7.json","graph_json":"https://pith.science/api/pith-number/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/graph.json","events_json":"https://pith.science/api/pith-number/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/events.json","paper":"https://pith.science/paper/LF7SPG6G"},"agent_actions":{"view_html":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7","download_json":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7.json","view_paper":"https://pith.science/paper/LF7SPG6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04054&json=true","fetch_graph":"https://pith.science/api/pith-number/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/graph.json","fetch_events":"https://pith.science/api/pith-number/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/action/storage_attestation","attest_author":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/action/author_attestation","sign_citation":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/action/citation_signature","submit_replication":"https://pith.science/pith/LF7SPG6G6HIVTW2ZXRZ5OFHMA7/action/replication_record"}},"created_at":"2026-07-05T09:21:47.640765+00:00","updated_at":"2026-07-05T09:21:47.640765+00:00"}