{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4252E4AR3EKVSHSM5NPQJY5HQL","short_pith_number":"pith:4252E4AR","canonical_record":{"source":{"id":"1803.04926","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T16:35:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2b3e964cd0cb778cbdbcdefd2c1bb5df322704a14b5b0925abb708e7b75d2463","abstract_canon_sha256":"aaf2a261a6544e7613800ca638c474561de0d45e04abbe41c8d6bcfa41058b20"},"schema_version":"1.0"},"canonical_sha256":"e6bba27011d915591e4ceb5f04e3a782e6133d35cf651ffa5c47cbd3b859664c","source":{"kind":"arxiv","id":"1803.04926","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04926","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04926v3","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04926","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"4252E4AR3EKV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4252E4AR3EKVSHSM","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4252E4AR","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4252E4AR3EKVSHSM5NPQJY5HQL","target":"record","payload":{"canonical_record":{"source":{"id":"1803.04926","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T16:35:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2b3e964cd0cb778cbdbcdefd2c1bb5df322704a14b5b0925abb708e7b75d2463","abstract_canon_sha256":"aaf2a261a6544e7613800ca638c474561de0d45e04abbe41c8d6bcfa41058b20"},"schema_version":"1.0"},"canonical_sha256":"e6bba27011d915591e4ceb5f04e3a782e6133d35cf651ffa5c47cbd3b859664c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:13.442248Z","signature_b64":"Zh+0FAtTbaEjx+rdWabHjd46CUjn5dckSwl3U5nb7bMdiIsYNlK4FUppArkhH+ZD6j3sQj+fHI+T/2Rb8VylAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6bba27011d915591e4ceb5f04e3a782e6133d35cf651ffa5c47cbd3b859664c","last_reissued_at":"2026-05-18T00:20:13.441764Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:13.441764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.04926","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXZbDoNWKcZiS8IWVCNbdKyIOZUh3B1S0juPqYO8uq1RneQQGB5tqSuIGb0h4WCf5DK3awP2lOKPZtUlGoWnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:49:24.752991Z"},"content_sha256":"985804ab61cdcd7015044ae490ebe82b4536e1e5ecf59fadfe915568c0967e48","schema_version":"1.0","event_id":"sha256:985804ab61cdcd7015044ae490ebe82b4536e1e5ecf59fadfe915568c0967e48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4252E4AR3EKVSHSM5NPQJY5HQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Reinforcement Learning with Monte-Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Owain Evans, Sebastian Schulze","submitted_at":"2018-03-13T16:35:25Z","abstract_excerpt":"Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson sampling, and random exploration do not help with ARL. We relate ARL in tabular environments to Bayes-Adaptive MDPs. We provide an ARL algorithm using Monte-Carlo Tree Search that is asymptotically Bayes optimal. Experimentally, this algorithm is near-optimal on small Bandit problems and MDPs. On larger MDPs it outperforms a Q-learner augmented with speciali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04926","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iBtE39gwr/3wRdYOarlMk5197RgoG7tvH4lVEpc0Frg9ge9PthWRbEYY3+3NneN86qh3/m04lw9XJYO5Y59mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:49:24.753363Z"},"content_sha256":"539d6fde4c23ceadb61f766488c6bbc8b5abd19536d858461f1d3886fb3e39ec","schema_version":"1.0","event_id":"sha256:539d6fde4c23ceadb61f766488c6bbc8b5abd19536d858461f1d3886fb3e39ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4252E4AR3EKVSHSM5NPQJY5HQL/bundle.json","state_url":"https://pith.science/pith/4252E4AR3EKVSHSM5NPQJY5HQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4252E4AR3EKVSHSM5NPQJY5HQL/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":"2026-06-10T20:49:24Z","links":{"resolver":"https://pith.science/pith/4252E4AR3EKVSHSM5NPQJY5HQL","bundle":"https://pith.science/pith/4252E4AR3EKVSHSM5NPQJY5HQL/bundle.json","state":"https://pith.science/pith/4252E4AR3EKVSHSM5NPQJY5HQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4252E4AR3EKVSHSM5NPQJY5HQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4252E4AR3EKVSHSM5NPQJY5HQL","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":"aaf2a261a6544e7613800ca638c474561de0d45e04abbe41c8d6bcfa41058b20","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T16:35:25Z","title_canon_sha256":"2b3e964cd0cb778cbdbcdefd2c1bb5df322704a14b5b0925abb708e7b75d2463"},"schema_version":"1.0","source":{"id":"1803.04926","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04926","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04926v3","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04926","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"4252E4AR3EKV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4252E4AR3EKVSHSM","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4252E4AR","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:539d6fde4c23ceadb61f766488c6bbc8b5abd19536d858461f1d3886fb3e39ec","target":"graph","created_at":"2026-05-18T00:20:13Z","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":"Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson sampling, and random exploration do not help with ARL. We relate ARL in tabular environments to Bayes-Adaptive MDPs. We provide an ARL algorithm using Monte-Carlo Tree Search that is asymptotically Bayes optimal. Experimentally, this algorithm is near-optimal on small Bandit problems and MDPs. On larger MDPs it outperforms a Q-learner augmented with speciali","authors_text":"Owain Evans, Sebastian Schulze","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T16:35:25Z","title":"Active Reinforcement Learning with Monte-Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04926","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":"sha256:985804ab61cdcd7015044ae490ebe82b4536e1e5ecf59fadfe915568c0967e48","target":"record","created_at":"2026-05-18T00:20:13Z","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":"aaf2a261a6544e7613800ca638c474561de0d45e04abbe41c8d6bcfa41058b20","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T16:35:25Z","title_canon_sha256":"2b3e964cd0cb778cbdbcdefd2c1bb5df322704a14b5b0925abb708e7b75d2463"},"schema_version":"1.0","source":{"id":"1803.04926","kind":"arxiv","version":3}},"canonical_sha256":"e6bba27011d915591e4ceb5f04e3a782e6133d35cf651ffa5c47cbd3b859664c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6bba27011d915591e4ceb5f04e3a782e6133d35cf651ffa5c47cbd3b859664c","first_computed_at":"2026-05-18T00:20:13.441764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:13.441764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zh+0FAtTbaEjx+rdWabHjd46CUjn5dckSwl3U5nb7bMdiIsYNlK4FUppArkhH+ZD6j3sQj+fHI+T/2Rb8VylAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:13.442248Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.04926","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:985804ab61cdcd7015044ae490ebe82b4536e1e5ecf59fadfe915568c0967e48","sha256:539d6fde4c23ceadb61f766488c6bbc8b5abd19536d858461f1d3886fb3e39ec"],"state_sha256":"d3a97b344ce6ff62d0b32e14304a196f63a78e09c62d7ceb5ca57da8d03b70bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8p+zTy75aVBgDGMlwNtDnV7W0TzRmLlGPUg6jIeO5Y/wLGW0Gxhzfjmx+AYNZFPXsXL/VJNDErv1E0hI2O6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T20:49:24.755388Z","bundle_sha256":"535ff7996fa113021e63dcf41e31083a8a7fc3ecfddcf12cede4cd53b91b3398"}}