{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YAJIMGQJC6ZOPF5KIIXGMCTY2Q","short_pith_number":"pith:YAJIMGQJ","schema_version":"1.0","canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","source":{"kind":"arxiv","id":"1905.10404","version":1},"attestation_state":"computed","paper":{"title":"InfoRL: Interpretable Reinforcement Learning using Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aadil Hayat, Utsav Singh, Vinay P. Namboodiri","submitted_at":"2019-05-24T18:47:09Z","abstract_excerpt":"Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL). But most of the algorithms focus on learning a single best policy to perform a given set of tasks. In this paper, we focus on an algorithm that learns to not just perform a task but different ways to perform the same task. As we know when the environment is complex enough there always exists multiple ways to perform a task. We show that using the concept of information maximiza"},"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":"1905.10404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:47:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bb1afbfa46d10a7e2149a59520ac99dfa9c513ec94ac81ce2d8ee6ed446ef1e5","abstract_canon_sha256":"3eaf19471335d0f51c072c4f5434968934725b4daffd06cb80e75f6fa0704560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.642511Z","signature_b64":"49bubOeeXjcxeYqIBHIO4sBqk+e9n2PXXegIyh8KwBwbNtlFPrDxoL2SE+gSpEa31ToLcqcfTbulMNNI2NUpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","last_reissued_at":"2026-05-17T23:45:08.641834Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.641834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfoRL: Interpretable Reinforcement Learning using Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aadil Hayat, Utsav Singh, Vinay P. Namboodiri","submitted_at":"2019-05-24T18:47:09Z","abstract_excerpt":"Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL). But most of the algorithms focus on learning a single best policy to perform a given set of tasks. In this paper, we focus on an algorithm that learns to not just perform a task but different ways to perform the same task. As we know when the environment is complex enough there always exists multiple ways to perform a task. We show that using the concept of information maximiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10404","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":"1905.10404","created_at":"2026-05-17T23:45:08.641937+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10404v1","created_at":"2026-05-17T23:45:08.641937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10404","created_at":"2026-05-17T23:45:08.641937+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAJIMGQJC6ZO","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAJIMGQJC6ZOPF5K","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAJIMGQJ","created_at":"2026-05-18T12:33:33.725879+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/YAJIMGQJC6ZOPF5KIIXGMCTY2Q","json":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q.json","graph_json":"https://pith.science/api/pith-number/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/graph.json","events_json":"https://pith.science/api/pith-number/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/events.json","paper":"https://pith.science/paper/YAJIMGQJ"},"agent_actions":{"view_html":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q","download_json":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q.json","view_paper":"https://pith.science/paper/YAJIMGQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10404&json=true","fetch_graph":"https://pith.science/api/pith-number/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/action/storage_attestation","attest_author":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/action/author_attestation","sign_citation":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/action/citation_signature","submit_replication":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/action/replication_record"}},"created_at":"2026-05-17T23:45:08.641937+00:00","updated_at":"2026-05-17T23:45:08.641937+00:00"}