{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G6KJHD6IQA6BFHZTEE64EF4TES","short_pith_number":"pith:G6KJHD6I","canonical_record":{"source":{"id":"2007.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T04:30:47Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"341a2363c8c0f06cc82aeb0930a14ee3a7cfd50b619b94c7420ee87b66019be3","abstract_canon_sha256":"229382fc0515d5e3204d90a427553c1fafd11eed64c9a5269d80a6647947c008"},"schema_version":"1.0"},"canonical_sha256":"3794938fc8803c129f33213dc217932487fc84cdd8f19d446ec555d174ff6d7b","source":{"kind":"arxiv","id":"2007.00869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00869","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00869v1","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00869","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"G6KJHD6IQA6B","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"G6KJHD6IQA6BFHZT","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"G6KJHD6I","created_at":"2026-07-05T01:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G6KJHD6IQA6BFHZTEE64EF4TES","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T04:30:47Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"341a2363c8c0f06cc82aeb0930a14ee3a7cfd50b619b94c7420ee87b66019be3","abstract_canon_sha256":"229382fc0515d5e3204d90a427553c1fafd11eed64c9a5269d80a6647947c008"},"schema_version":"1.0"},"canonical_sha256":"3794938fc8803c129f33213dc217932487fc84cdd8f19d446ec555d174ff6d7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:42.006989Z","signature_b64":"mSeRjrgQGdGS9pZy7VsksONG9bKZ6SZCsUBNx42mS7pvsoIfMaRrYDq81AO9a7wlBXtCqiI/I3gToQodE8flAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3794938fc8803c129f33213dc217932487fc84cdd8f19d446ec555d174ff6d7b","last_reissued_at":"2026-07-05T01:15:42.006525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:42.006525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00869","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":"2026-07-05T01:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cd7pZ53baPKvMrFwrNpXp7GLfm+UXvZDwJu810uN334a7kEB2RPD3eJZrLVlUC4FHan02AhXaKhFayw5E4U/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:12:06.373841Z"},"content_sha256":"1eb8f8723f723af54fe2f9e04b4dab7fabcbe6c1e9caaeb535baf62635d5c715","schema_version":"1.0","event_id":"sha256:1eb8f8723f723af54fe2f9e04b4dab7fabcbe6c1e9caaeb535baf62635d5c715"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G6KJHD6IQA6BFHZTEE64EF4TES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"{\\epsilon}-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi-Guhn Lee, Michael Gimelfarb, Scott Sanner","submitted_at":"2020-07-02T04:30:47Z","abstract_excerpt":"Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequently used forms of exploration. However, a key limitation of this policy is the specification of $\\varepsilon$. In this paper, we provide a novel Bayesian perspective of $\\varepsilon$ as a measure of the uniformity of the Q-value function. We introduce a closed-form Bayesian model update based on B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00869","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/2007.00869/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":"2026-07-05T01:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xOqd3Jg+37xWZtnnDiauxQs3RVJrVwx6R7BBePpGPZhdpX/+mW5DhTaF76sOsnM+7o4Zz2NyH7Xb4Nc0MYODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:12:06.374347Z"},"content_sha256":"649dfcd61d8f46003f14edc5d6b4ed41bdffe03a7096bd9456aefd1da86f1c79","schema_version":"1.0","event_id":"sha256:649dfcd61d8f46003f14edc5d6b4ed41bdffe03a7096bd9456aefd1da86f1c79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6KJHD6IQA6BFHZTEE64EF4TES/bundle.json","state_url":"https://pith.science/pith/G6KJHD6IQA6BFHZTEE64EF4TES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6KJHD6IQA6BFHZTEE64EF4TES/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":"2026-08-03T17:12:06Z","links":{"resolver":"https://pith.science/pith/G6KJHD6IQA6BFHZTEE64EF4TES","bundle":"https://pith.science/pith/G6KJHD6IQA6BFHZTEE64EF4TES/bundle.json","state":"https://pith.science/pith/G6KJHD6IQA6BFHZTEE64EF4TES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6KJHD6IQA6BFHZTEE64EF4TES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G6KJHD6IQA6BFHZTEE64EF4TES","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":"229382fc0515d5e3204d90a427553c1fafd11eed64c9a5269d80a6647947c008","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T04:30:47Z","title_canon_sha256":"341a2363c8c0f06cc82aeb0930a14ee3a7cfd50b619b94c7420ee87b66019be3"},"schema_version":"1.0","source":{"id":"2007.00869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00869","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00869v1","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00869","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"G6KJHD6IQA6B","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"G6KJHD6IQA6BFHZT","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"G6KJHD6I","created_at":"2026-07-05T01:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:649dfcd61d8f46003f14edc5d6b4ed41bdffe03a7096bd9456aefd1da86f1c79","target":"graph","created_at":"2026-07-05T01:15:42Z","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/2007.00869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequently used forms of exploration. However, a key limitation of this policy is the specification of $\\varepsilon$. In this paper, we provide a novel Bayesian perspective of $\\varepsilon$ as a measure of the uniformity of the Q-value function. We introduce a closed-form Bayesian model update based on B","authors_text":"Chi-Guhn Lee, Michael Gimelfarb, Scott Sanner","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T04:30:47Z","title":"{\\epsilon}-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00869","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":"sha256:1eb8f8723f723af54fe2f9e04b4dab7fabcbe6c1e9caaeb535baf62635d5c715","target":"record","created_at":"2026-07-05T01:15:42Z","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":"229382fc0515d5e3204d90a427553c1fafd11eed64c9a5269d80a6647947c008","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T04:30:47Z","title_canon_sha256":"341a2363c8c0f06cc82aeb0930a14ee3a7cfd50b619b94c7420ee87b66019be3"},"schema_version":"1.0","source":{"id":"2007.00869","kind":"arxiv","version":1}},"canonical_sha256":"3794938fc8803c129f33213dc217932487fc84cdd8f19d446ec555d174ff6d7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3794938fc8803c129f33213dc217932487fc84cdd8f19d446ec555d174ff6d7b","first_computed_at":"2026-07-05T01:15:42.006525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:42.006525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mSeRjrgQGdGS9pZy7VsksONG9bKZ6SZCsUBNx42mS7pvsoIfMaRrYDq81AO9a7wlBXtCqiI/I3gToQodE8flAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:42.006989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1eb8f8723f723af54fe2f9e04b4dab7fabcbe6c1e9caaeb535baf62635d5c715","sha256:649dfcd61d8f46003f14edc5d6b4ed41bdffe03a7096bd9456aefd1da86f1c79"],"state_sha256":"79ccffa2d1aee9a839f45610bc71343fc236f7a158435a8105f95ef83ab95e1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkLwCoXBH7cHhk8chfPKEP1jYbcJ/GyKY18Ow+3+uUqEDtLrcL8RDHwnpsZLyRgXk22Lo5UWIE/n94evp7aMDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:12:06.380369Z","bundle_sha256":"7d074357a428df3efb71b1071d69a4dfb9e77c0dd5c7c19970414fe9bbc30621"}}