{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OLU234XGMVAXCPLOFTPHKLSXY5","short_pith_number":"pith:OLU234XG","canonical_record":{"source":{"id":"2204.03771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-07T23:00:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c29537f97e04f3698fb95c79988604d2c9f2c157bdab824223181c79adcc6e54","abstract_canon_sha256":"2722ed711f57faa4c5e4e28b8a59908c25763fce86ff734cf1e1df78b465435c"},"schema_version":"1.0"},"canonical_sha256":"72e9adf2e66541713d6e2cde752e57c75ea4ee02c6cdae707c1ed5bff9168459","source":{"kind":"arxiv","id":"2204.03771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03771","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03771v1","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03771","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"OLU234XGMVAX","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"OLU234XGMVAXCPLO","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"OLU234XG","created_at":"2026-07-05T04:12:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OLU234XGMVAXCPLOFTPHKLSXY5","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-07T23:00:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c29537f97e04f3698fb95c79988604d2c9f2c157bdab824223181c79adcc6e54","abstract_canon_sha256":"2722ed711f57faa4c5e4e28b8a59908c25763fce86ff734cf1e1df78b465435c"},"schema_version":"1.0"},"canonical_sha256":"72e9adf2e66541713d6e2cde752e57c75ea4ee02c6cdae707c1ed5bff9168459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:41.690242Z","signature_b64":"/9SLZXCtqEeEqDnS8zI54RsKjRNEwlgYGmytdSBtlGEvA/nV+gemErkDR3giiby0Gz58thEZ6eb6qqzs2c0iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72e9adf2e66541713d6e2cde752e57c75ea4ee02c6cdae707c1ed5bff9168459","last_reissued_at":"2026-07-05T04:12:41.689879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:41.689879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03771","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":"2026-07-05T04:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJOxrEwT6H3GEcibslccMsRrdTbU6NBmhkr8XPTjmf4end1u5tw13j/50MyhwVVNexbulguViTmv1KO+yAzpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:15:59.719236Z"},"content_sha256":"31f8149b0fd24b5b4e8fbab40a13e4fd9e52f1640b42f0b4550a6f15258bce45","schema_version":"1.0","event_id":"sha256:31f8149b0fd24b5b4e8fbab40a13e4fd9e52f1640b42f0b4550a6f15258bce45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OLU234XGMVAXCPLOFTPHKLSXY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-learning with online random forests","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joosung Min, Lloyd T. Elliott","submitted_at":"2022-04-07T23:00:39Z","abstract_excerpt":"$Q$-learning is the most fundamental model-free reinforcement learning algorithm. Deployment of $Q$-learning requires approximation of the state-action value function (also known as the $Q$-function). In this work, we provide online random forests as $Q$-function approximators and propose a novel method wherein the random forest is grown as learning proceeds (through expanding forests). We demonstrate improved performance of our methods over state-of-the-art Deep $Q$-Networks in two OpenAI gyms (`blackjack' and `inverted pendulum') but not in the `lunar lander' gym. We suspect that the resilie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03771","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.03771/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+M85yGw8CmQuPLcQlFeOjxyNQgy+EpxUMrKaD6EPur5it2zxJz0ZdlA4Q2eNprdtl0q0HyX+1iI53H426xyOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:15:59.719998Z"},"content_sha256":"b0d9c8891a995be6d68c6ab5b42758620e849025a75f519131c8e7af7214be62","schema_version":"1.0","event_id":"sha256:b0d9c8891a995be6d68c6ab5b42758620e849025a75f519131c8e7af7214be62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLU234XGMVAXCPLOFTPHKLSXY5/bundle.json","state_url":"https://pith.science/pith/OLU234XGMVAXCPLOFTPHKLSXY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLU234XGMVAXCPLOFTPHKLSXY5/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":"2026-08-17T23:15:59Z","links":{"resolver":"https://pith.science/pith/OLU234XGMVAXCPLOFTPHKLSXY5","bundle":"https://pith.science/pith/OLU234XGMVAXCPLOFTPHKLSXY5/bundle.json","state":"https://pith.science/pith/OLU234XGMVAXCPLOFTPHKLSXY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLU234XGMVAXCPLOFTPHKLSXY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OLU234XGMVAXCPLOFTPHKLSXY5","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":"2722ed711f57faa4c5e4e28b8a59908c25763fce86ff734cf1e1df78b465435c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-07T23:00:39Z","title_canon_sha256":"c29537f97e04f3698fb95c79988604d2c9f2c157bdab824223181c79adcc6e54"},"schema_version":"1.0","source":{"id":"2204.03771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03771","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03771v1","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03771","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"OLU234XGMVAX","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"OLU234XGMVAXCPLO","created_at":"2026-07-05T04:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"OLU234XG","created_at":"2026-07-05T04:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:b0d9c8891a995be6d68c6ab5b42758620e849025a75f519131c8e7af7214be62","target":"graph","created_at":"2026-07-05T04:12:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.03771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"$Q$-learning is the most fundamental model-free reinforcement learning algorithm. Deployment of $Q$-learning requires approximation of the state-action value function (also known as the $Q$-function). In this work, we provide online random forests as $Q$-function approximators and propose a novel method wherein the random forest is grown as learning proceeds (through expanding forests). We demonstrate improved performance of our methods over state-of-the-art Deep $Q$-Networks in two OpenAI gyms (`blackjack' and `inverted pendulum') but not in the `lunar lander' gym. We suspect that the resilie","authors_text":"Joosung Min, Lloyd T. Elliott","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-07T23:00:39Z","title":"Q-learning with online random forests"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03771","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":"sha256:31f8149b0fd24b5b4e8fbab40a13e4fd9e52f1640b42f0b4550a6f15258bce45","target":"record","created_at":"2026-07-05T04:12:41Z","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":"2722ed711f57faa4c5e4e28b8a59908c25763fce86ff734cf1e1df78b465435c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-07T23:00:39Z","title_canon_sha256":"c29537f97e04f3698fb95c79988604d2c9f2c157bdab824223181c79adcc6e54"},"schema_version":"1.0","source":{"id":"2204.03771","kind":"arxiv","version":1}},"canonical_sha256":"72e9adf2e66541713d6e2cde752e57c75ea4ee02c6cdae707c1ed5bff9168459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72e9adf2e66541713d6e2cde752e57c75ea4ee02c6cdae707c1ed5bff9168459","first_computed_at":"2026-07-05T04:12:41.689879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:41.689879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/9SLZXCtqEeEqDnS8zI54RsKjRNEwlgYGmytdSBtlGEvA/nV+gemErkDR3giiby0Gz58thEZ6eb6qqzs2c0iAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:41.690242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31f8149b0fd24b5b4e8fbab40a13e4fd9e52f1640b42f0b4550a6f15258bce45","sha256:b0d9c8891a995be6d68c6ab5b42758620e849025a75f519131c8e7af7214be62"],"state_sha256":"cc320b045d40921e73a8e738d11762db2c44c34f5e81b2bfe610fb3c39034297"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnD4aMFX+03n6gOHD5t6Mzoak7I46Fiqjt4XEQ40bL6K3wiT0VYILJ7Rkz80b8xJbubZDnja55LW7HZnDKqeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:15:59.727921Z","bundle_sha256":"410df40615cca2b219ec9e183772307c593ba273d0d08874296470b4c1b651c6"}}