{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:TP7BZ57TSXIG4SB2W6PD7VKGHC","short_pith_number":"pith:TP7BZ57T","canonical_record":{"source":{"id":"1709.06293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-19T08:36:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c2ae5b405b8b67aba9b11d74a7a6e985f71ab01722400bd24cb13a6477cde3f9","abstract_canon_sha256":"372b12d33b0bc697468cbe1ccc282149ed6260b770dad9c72a720243ba40fcfd"},"schema_version":"1.0"},"canonical_sha256":"9bfe1cf7f395d06e483ab79e3fd54638afb15d0a7b3f47cd3cf7ad2b6217d614","source":{"kind":"arxiv","id":"1709.06293","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06293","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06293v3","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06293","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"pith_short_12","alias_value":"TP7BZ57TSXIG","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TP7BZ57TSXIG4SB2","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TP7BZ57T","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:TP7BZ57TSXIG4SB2W6PD7VKGHC","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-19T08:36:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c2ae5b405b8b67aba9b11d74a7a6e985f71ab01722400bd24cb13a6477cde3f9","abstract_canon_sha256":"372b12d33b0bc697468cbe1ccc282149ed6260b770dad9c72a720243ba40fcfd"},"schema_version":"1.0"},"canonical_sha256":"9bfe1cf7f395d06e483ab79e3fd54638afb15d0a7b3f47cd3cf7ad2b6217d614","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:57.246586Z","signature_b64":"k9HWCZ/T2Mo0b9no6lQit+xTSREYXpAQ46UioiSCLBiT5DmwdnJp1Icq/tDB3O6DGjSV7pA6F6JtJ9WgNNRFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bfe1cf7f395d06e483ab79e3fd54638afb15d0a7b3f47cd3cf7ad2b6217d614","last_reissued_at":"2026-05-18T00:32:57.246062Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:57.246062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06293","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3r551cdlifhg91zhWh7hdtHz78zFEfcHNCP7X2eVDfwHa6giPGnBvRy4rehZm9nVeF1v1+CrkpfNc30D7PmADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:32:30.533344Z"},"content_sha256":"abe4091f9afb50d050f147ee245150459b25b73873e34c0a287be729da799859","schema_version":"1.0","event_id":"sha256:abe4091f9afb50d050f147ee245150459b25b73873e34c0a287be729da799859"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:TP7BZ57TSXIG4SB2W6PD7VKGHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kyungjae Lee, Songhwai Oh, Sungjoon Choi","submitted_at":"2017-09-19T08:36:21Z","abstract_excerpt":"In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyze the optimality condition of a sparse MDP. Then, we propose a sparse value iteration method which solves a sparse MDP and then prove the convergence and optimality of sparse value iteration using the Banach fixed point theorem. The proposed sparse MDP is compared to soft MDPs wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06293","kind":"arxiv","version":3},"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":"2026-05-18T00:32:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zfu5DXHPmT7fue0l4ST/m2PkvURyYIbpAErH9Dz9RXDUBmznd/XvlpfAuTUS4PK+AupPTtUR/dymdvudT4qJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:32:30.533839Z"},"content_sha256":"ce0101dde8fb20d358a41126c7fa8c79ec0daf90d57af55ce9b0c907f192287d","schema_version":"1.0","event_id":"sha256:ce0101dde8fb20d358a41126c7fa8c79ec0daf90d57af55ce9b0c907f192287d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/bundle.json","state_url":"https://pith.science/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/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":"2026-05-28T13:32:30Z","links":{"resolver":"https://pith.science/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC","bundle":"https://pith.science/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/bundle.json","state":"https://pith.science/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TP7BZ57TSXIG4SB2W6PD7VKGHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TP7BZ57TSXIG4SB2W6PD7VKGHC","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":"372b12d33b0bc697468cbe1ccc282149ed6260b770dad9c72a720243ba40fcfd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-19T08:36:21Z","title_canon_sha256":"c2ae5b405b8b67aba9b11d74a7a6e985f71ab01722400bd24cb13a6477cde3f9"},"schema_version":"1.0","source":{"id":"1709.06293","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06293","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06293v3","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06293","created_at":"2026-05-18T00:32:57Z"},{"alias_kind":"pith_short_12","alias_value":"TP7BZ57TSXIG","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TP7BZ57TSXIG4SB2","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TP7BZ57T","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce0101dde8fb20d358a41126c7fa8c79ec0daf90d57af55ce9b0c907f192287d","target":"graph","created_at":"2026-05-18T00:32:57Z","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":"In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyze the optimality condition of a sparse MDP. Then, we propose a sparse value iteration method which solves a sparse MDP and then prove the convergence and optimality of sparse value iteration using the Banach fixed point theorem. The proposed sparse MDP is compared to soft MDPs wh","authors_text":"Kyungjae Lee, Songhwai Oh, Sungjoon Choi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-19T08:36:21Z","title":"Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06293","kind":"arxiv","version":3},"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:abe4091f9afb50d050f147ee245150459b25b73873e34c0a287be729da799859","target":"record","created_at":"2026-05-18T00:32:57Z","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":"372b12d33b0bc697468cbe1ccc282149ed6260b770dad9c72a720243ba40fcfd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-19T08:36:21Z","title_canon_sha256":"c2ae5b405b8b67aba9b11d74a7a6e985f71ab01722400bd24cb13a6477cde3f9"},"schema_version":"1.0","source":{"id":"1709.06293","kind":"arxiv","version":3}},"canonical_sha256":"9bfe1cf7f395d06e483ab79e3fd54638afb15d0a7b3f47cd3cf7ad2b6217d614","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bfe1cf7f395d06e483ab79e3fd54638afb15d0a7b3f47cd3cf7ad2b6217d614","first_computed_at":"2026-05-18T00:32:57.246062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:57.246062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9HWCZ/T2Mo0b9no6lQit+xTSREYXpAQ46UioiSCLBiT5DmwdnJp1Icq/tDB3O6DGjSV7pA6F6JtJ9WgNNRFCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:57.246586Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06293","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abe4091f9afb50d050f147ee245150459b25b73873e34c0a287be729da799859","sha256:ce0101dde8fb20d358a41126c7fa8c79ec0daf90d57af55ce9b0c907f192287d"],"state_sha256":"4188c3f8d66278a187ff15c3d2fbb5e3909543487e9d267b22536cd05fdeaa96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urncqVhT9Q3lFPJIltwSfzeWC601IV9jJM2NpDMu7f4BK6KvXi+jMeTiRLlfR8kqTUc/yFkgFPjWa5yZTOZICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:32:30.536267Z","bundle_sha256":"def3bf90b12de174bfd8997c9028e95b936c3aee862ddd68da018db38ef39124"}}