{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","short_pith_number":"pith:Q6ILPJUQ","canonical_record":{"source":{"id":"1806.05415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"e2d2806327888403b635b151312c8c89f9e7ed59087d1eac2f0f46c8589a4d50","abstract_canon_sha256":"a8f97e29874161584be851892a0b3d2cf5c04aad47e0f06c5496b29ba44cc781"},"schema_version":"1.0"},"canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","source":{"kind":"arxiv","id":"1806.05415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05415","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05415v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05415","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"Q6ILPJUQ2Z3W","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6ILPJUQ2Z3WO3OE","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6ILPJUQ","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"e2d2806327888403b635b151312c8c89f9e7ed59087d1eac2f0f46c8589a4d50","abstract_canon_sha256":"a8f97e29874161584be851892a0b3d2cf5c04aad47e0f06c5496b29ba44cc781"},"schema_version":"1.0"},"canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.042691Z","signature_b64":"Y/VaRWjoyuDtnJkuA2N07ImJ8my7CuGTLTQoBneYCrgCxHxd6fLEBQwjK8phjhDh9ca84FDwUDr0UTSNmJsaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","last_reissued_at":"2026-05-18T00:13:16.041974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.041974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05415","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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bbp+53UNY/5JAJlXcdtIOycnEZjG6ZACmwD1wr0for6ne/lygXikLtisP+dy78JWLQ7T/jPFqgfMQyDy9NF7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:42:42.350897Z"},"content_sha256":"5f51e018cf8259b857546538bf0d8c05528dc6164559557bd7a2038d4052549d","schema_version":"1.0","event_id":"sha256:5f51e018cf8259b857546538bf0d8c05528dc6164559557bd7a2038d4052549d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Configurable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alberto Maria Metelli, Marcello Restelli, Mirco Mutti","submitted_at":"2018-06-14T08:54:38Z","abstract_excerpt":"In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05415","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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IgazVQdTQNqG8TetgBsLNDbDce8ekp3jJb0wvEOtmgFhy976qqmQjZpiUXEFmsk8FYD646OL5uCZQeDE79nAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:42:42.351225Z"},"content_sha256":"ec33e115057552cf6ae9d711e72554ac65f91cd3af8fba0a40eb7ab1255900f3","schema_version":"1.0","event_id":"sha256:ec33e115057552cf6ae9d711e72554ac65f91cd3af8fba0a40eb7ab1255900f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/bundle.json","state_url":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/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":"2026-06-09T12:42:42Z","links":{"resolver":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","bundle":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/bundle.json","state":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","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":"a8f97e29874161584be851892a0b3d2cf5c04aad47e0f06c5496b29ba44cc781","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","title_canon_sha256":"e2d2806327888403b635b151312c8c89f9e7ed59087d1eac2f0f46c8589a4d50"},"schema_version":"1.0","source":{"id":"1806.05415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05415","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05415v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05415","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"Q6ILPJUQ2Z3W","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6ILPJUQ2Z3WO3OE","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6ILPJUQ","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:ec33e115057552cf6ae9d711e72554ac65f91cd3af8fba0a40eb7ab1255900f3","target":"graph","created_at":"2026-05-18T00:13:16Z","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 many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evalua","authors_text":"Alberto Maria Metelli, Marcello Restelli, Mirco Mutti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","title":"Configurable Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05415","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":"sha256:5f51e018cf8259b857546538bf0d8c05528dc6164559557bd7a2038d4052549d","target":"record","created_at":"2026-05-18T00:13:16Z","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":"a8f97e29874161584be851892a0b3d2cf5c04aad47e0f06c5496b29ba44cc781","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","title_canon_sha256":"e2d2806327888403b635b151312c8c89f9e7ed59087d1eac2f0f46c8589a4d50"},"schema_version":"1.0","source":{"id":"1806.05415","kind":"arxiv","version":1}},"canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","first_computed_at":"2026-05-18T00:13:16.041974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:16.041974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y/VaRWjoyuDtnJkuA2N07ImJ8my7CuGTLTQoBneYCrgCxHxd6fLEBQwjK8phjhDh9ca84FDwUDr0UTSNmJsaAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:16.042691Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f51e018cf8259b857546538bf0d8c05528dc6164559557bd7a2038d4052549d","sha256:ec33e115057552cf6ae9d711e72554ac65f91cd3af8fba0a40eb7ab1255900f3"],"state_sha256":"df885fe1d22b5d3167de8bfe7f7e1a8a781229086ccf684b339d1e0edf1be812"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYTIQmf+XASKFL8dK6MBNmfY3P9iGZLcfT3b2+QGlqpNe3xW5//Os3JuGpqvPaO4MBRp+bRnJBNguKQAdYbOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:42:42.352978Z","bundle_sha256":"e4cb905fdce33c3fa156129b5325fbed90fc3e3050f474fca8905bd93f85d306"}}