{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KULZUIPB3GZX5M2OSJGLKU6SLT","short_pith_number":"pith:KULZUIPB","schema_version":"1.0","canonical_sha256":"55179a21e1d9b37eb34e924cb553d25cc2ef241b9ec9418aae12574f7f1c998d","source":{"kind":"arxiv","id":"1611.09894","version":1},"attestation_state":"computed","paper":{"title":"Exploration for Multi-task Reinforcement Learning with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Balaraman Ravindran, JS Suhas, Sai Praveen Bangaru","submitted_at":"2016-11-29T21:32:25Z","abstract_excerpt":"Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We eva"},"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":"1611.09894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-29T21:32:25Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"8f980566e52def5264b857fb50925be71259ab5650f1a19d2d986b5bbe4246ad","abstract_canon_sha256":"22a14073a092798352f194244268175901786a448b64096ae7f5b790b99b79b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:05.110723Z","signature_b64":"QkWga9K07VourUqA6Cr5BTZDJmKfnJEXb4s2vBzuaAJ+cqqJbgW8DY7kadGAZaOZ0xls52slSRHrVUttOyY8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55179a21e1d9b37eb34e924cb553d25cc2ef241b9ec9418aae12574f7f1c998d","last_reissued_at":"2026-05-18T00:56:05.110089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:05.110089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploration for Multi-task Reinforcement Learning with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Balaraman Ravindran, JS Suhas, Sai Praveen Bangaru","submitted_at":"2016-11-29T21:32:25Z","abstract_excerpt":"Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09894","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":"1611.09894","created_at":"2026-05-18T00:56:05.110271+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09894v1","created_at":"2026-05-18T00:56:05.110271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09894","created_at":"2026-05-18T00:56:05.110271+00:00"},{"alias_kind":"pith_short_12","alias_value":"KULZUIPB3GZX","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"KULZUIPB3GZX5M2O","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"KULZUIPB","created_at":"2026-05-18T12:30:29.479603+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/KULZUIPB3GZX5M2OSJGLKU6SLT","json":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT.json","graph_json":"https://pith.science/api/pith-number/KULZUIPB3GZX5M2OSJGLKU6SLT/graph.json","events_json":"https://pith.science/api/pith-number/KULZUIPB3GZX5M2OSJGLKU6SLT/events.json","paper":"https://pith.science/paper/KULZUIPB"},"agent_actions":{"view_html":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT","download_json":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT.json","view_paper":"https://pith.science/paper/KULZUIPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09894&json=true","fetch_graph":"https://pith.science/api/pith-number/KULZUIPB3GZX5M2OSJGLKU6SLT/graph.json","fetch_events":"https://pith.science/api/pith-number/KULZUIPB3GZX5M2OSJGLKU6SLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT/action/storage_attestation","attest_author":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT/action/author_attestation","sign_citation":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT/action/citation_signature","submit_replication":"https://pith.science/pith/KULZUIPB3GZX5M2OSJGLKU6SLT/action/replication_record"}},"created_at":"2026-05-18T00:56:05.110271+00:00","updated_at":"2026-05-18T00:56:05.110271+00:00"}