{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KULZUIPB3GZX5M2OSJGLKU6SLT","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":"22a14073a092798352f194244268175901786a448b64096ae7f5b790b99b79b9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-29T21:32:25Z","title_canon_sha256":"8f980566e52def5264b857fb50925be71259ab5650f1a19d2d986b5bbe4246ad"},"schema_version":"1.0","source":{"id":"1611.09894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.09894","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"1611.09894v1","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09894","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"KULZUIPB3GZX","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"KULZUIPB3GZX5M2O","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"KULZUIPB","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:eba34de97256829e1ea15608b8aa739945351703e001e53aded2988ea3a9018b","target":"graph","created_at":"2026-05-18T00:56:05Z","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"},"paper":{"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","authors_text":"Balaraman Ravindran, JS Suhas, Sai Praveen Bangaru","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-29T21:32:25Z","title":"Exploration for Multi-task Reinforcement Learning with Deep Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09894","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":"sha256:5a5c6b55b035ca62c6aed46d4d944336b7296465aecc9b605be80c3773a4ec41","target":"record","created_at":"2026-05-18T00:56:05Z","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":"22a14073a092798352f194244268175901786a448b64096ae7f5b790b99b79b9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-29T21:32:25Z","title_canon_sha256":"8f980566e52def5264b857fb50925be71259ab5650f1a19d2d986b5bbe4246ad"},"schema_version":"1.0","source":{"id":"1611.09894","kind":"arxiv","version":1}},"canonical_sha256":"55179a21e1d9b37eb34e924cb553d25cc2ef241b9ec9418aae12574f7f1c998d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55179a21e1d9b37eb34e924cb553d25cc2ef241b9ec9418aae12574f7f1c998d","first_computed_at":"2026-05-18T00:56:05.110089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:05.110089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkWga9K07VourUqA6Cr5BTZDJmKfnJEXb4s2vBzuaAJ+cqqJbgW8DY7kadGAZaOZ0xls52slSRHrVUttOyY8CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:05.110723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.09894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a5c6b55b035ca62c6aed46d4d944336b7296465aecc9b605be80c3773a4ec41","sha256:eba34de97256829e1ea15608b8aa739945351703e001e53aded2988ea3a9018b"],"state_sha256":"ca99f6167d6c97f11c956aa5b5e17aae7be8991bf9858276beb5cf9a76795f33"}