{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YAJIMGQJC6ZOPF5KIIXGMCTY2Q","short_pith_number":"pith:YAJIMGQJ","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"},"canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","source":{"kind":"arxiv","id":"1905.10404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10404","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10404v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10404","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"YAJIMGQJC6ZO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YAJIMGQJC6ZOPF5K","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YAJIMGQJ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YAJIMGQJC6ZOPF5KIIXGMCTY2Q","target":"record","payload":{"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"},"canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","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"},"source_kind":"arxiv","source_id":"1905.10404","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1F0DsX3jwrp/7oTBRcxHA+lspXuvrgOiHbjGJjhUNpMrmxbpHJvjbLy1USEhb5jgjbk5HJOpD3yukqk2/wRjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:10:27.637526Z"},"content_sha256":"d0e345bbd8f75f99334771697d97e82a141b2b1825f809e19f951e890d051a45","schema_version":"1.0","event_id":"sha256:d0e345bbd8f75f99334771697d97e82a141b2b1825f809e19f951e890d051a45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YAJIMGQJC6ZOPF5KIIXGMCTY2Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWPIUBQnNVGS1xcNTb2n/Sf6fasPK50y0w5yS1BfAVvTOEKPcAuPaskpwirX6AYkZSY/kk1Yvw6AqH2QcoZUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:10:27.637871Z"},"content_sha256":"4b767a309ff8b721a617c66e0ace2040a852a5986cb1a63d89d723102afd7b6b","schema_version":"1.0","event_id":"sha256:4b767a309ff8b721a617c66e0ace2040a852a5986cb1a63d89d723102afd7b6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/bundle.json","state_url":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T12:10:27Z","links":{"resolver":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q","bundle":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/bundle.json","state":"https://pith.science/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAJIMGQJC6ZOPF5KIIXGMCTY2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YAJIMGQJC6ZOPF5KIIXGMCTY2Q","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":"3eaf19471335d0f51c072c4f5434968934725b4daffd06cb80e75f6fa0704560","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:47:09Z","title_canon_sha256":"bb1afbfa46d10a7e2149a59520ac99dfa9c513ec94ac81ce2d8ee6ed446ef1e5"},"schema_version":"1.0","source":{"id":"1905.10404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10404","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10404v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10404","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"YAJIMGQJC6ZO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YAJIMGQJC6ZOPF5K","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YAJIMGQJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:4b767a309ff8b721a617c66e0ace2040a852a5986cb1a63d89d723102afd7b6b","target":"graph","created_at":"2026-05-17T23:45:08Z","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":"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","authors_text":"Aadil Hayat, Utsav Singh, Vinay P. Namboodiri","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:47:09Z","title":"InfoRL: Interpretable Reinforcement Learning using Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10404","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:d0e345bbd8f75f99334771697d97e82a141b2b1825f809e19f951e890d051a45","target":"record","created_at":"2026-05-17T23:45:08Z","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":"3eaf19471335d0f51c072c4f5434968934725b4daffd06cb80e75f6fa0704560","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:47:09Z","title_canon_sha256":"bb1afbfa46d10a7e2149a59520ac99dfa9c513ec94ac81ce2d8ee6ed446ef1e5"},"schema_version":"1.0","source":{"id":"1905.10404","kind":"arxiv","version":1}},"canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c012861a0917b2e797aa422e660a78d42aed02b3df6a207611b82aa7604fd664","first_computed_at":"2026-05-17T23:45:08.641834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:08.641834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"49bubOeeXjcxeYqIBHIO4sBqk+e9n2PXXegIyh8KwBwbNtlFPrDxoL2SE+gSpEa31ToLcqcfTbulMNNI2NUpCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:08.642511Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0e345bbd8f75f99334771697d97e82a141b2b1825f809e19f951e890d051a45","sha256:4b767a309ff8b721a617c66e0ace2040a852a5986cb1a63d89d723102afd7b6b"],"state_sha256":"79fd4fe81317a25722ae5c86b8227b7d70d2680cab678cc85fa404ffe6fcfbd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddYdp31YsirWUtCXRRJXokR5sImVPJoNeqJaAXrbGgYU2QVX9qeQye+6Hw//A9VMPxij0aU1O/QF/m3zHIAKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T12:10:27.639875Z","bundle_sha256":"97db2ea318650038e6751c97070acf9666181d42c5c9f575d40bcad83a21ed09"}}