{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AT4OJY6TWKOSMUBH3G67JKV3XX","short_pith_number":"pith:AT4OJY6T","canonical_record":{"source":{"id":"2010.05901","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"0ac4287a1a77977b1fabdf403dc9af859e0376fe5c172552a352505c94a88156","abstract_canon_sha256":"3c17258ccdd58798cf76a7dfbeaf02e453bfc276fa2326508b6966530c2a7bff"},"schema_version":"1.0"},"canonical_sha256":"04f8e4e3d3b29d265027d9bdf4aabbbdd6f5a0c8052256768edebb8fe226a003","source":{"kind":"arxiv","id":"2010.05901","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05901","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05901v2","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05901","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"AT4OJY6TWKOS","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_16","alias_value":"AT4OJY6TWKOSMUBH","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_8","alias_value":"AT4OJY6T","created_at":"2026-07-05T01:45:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AT4OJY6TWKOSMUBH3G67JKV3XX","target":"record","payload":{"canonical_record":{"source":{"id":"2010.05901","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"0ac4287a1a77977b1fabdf403dc9af859e0376fe5c172552a352505c94a88156","abstract_canon_sha256":"3c17258ccdd58798cf76a7dfbeaf02e453bfc276fa2326508b6966530c2a7bff"},"schema_version":"1.0"},"canonical_sha256":"04f8e4e3d3b29d265027d9bdf4aabbbdd6f5a0c8052256768edebb8fe226a003","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:31.038714Z","signature_b64":"tz86rjCNgSydY69j/MmIxgIaAqRSSC+of8U23Tu3Yeor5fUtf57i13njjwz5L9cpAWHwOUWertq7uawPZgRSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04f8e4e3d3b29d265027d9bdf4aabbbdd6f5a0c8052256768edebb8fe226a003","last_reissued_at":"2026-07-05T01:45:31.038331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:31.038331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.05901","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljkpS10Aap587AGvQz+V4Xw3QDl1DZWFOPsvWjP+tMIw+uG7TjF1kQ8ZxhOYOlkdU8Xd4B7MSAkeoxuudzIdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:01:14.070259Z"},"content_sha256":"512ac303e66308b2a596fac799689a0ee41cb5bdf210d9b1db13d2b6888e02cd","schema_version":"1.0","event_id":"sha256:512ac303e66308b2a596fac799689a0ee41cb5bdf210d9b1db13d2b6888e02cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AT4OJY6TWKOSMUBH3G67JKV3XX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearly Minimax Optimal Reward-free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Simon S. Du, Xiangyang Ji, Zihan Zhang","submitted_at":"2020-10-12T17:51:19Z","abstract_excerpt":"We study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple reward functions. This framework has two phases. In the exploration phase, the agent collects trajectories by interacting with the environment without using any reward signal. In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions. We give a new efficient algorithm, \\textbf{S}taged \\textbf{S}ampling + \\textbf{T}runcated \\textbf{P}lanning (\\algoname), which interacts with the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05901","kind":"arxiv","version":2},"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/2010.05901/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":"2026-07-05T01:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSU1xCrcvwKVnGEN0MkaFEoQHaqrmCVrxrLLgiTXW+fUJnjYXm3WdJwZvwG7G88OpwdlEql7q6KAzHxnmwODBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:01:14.070922Z"},"content_sha256":"8cd1c7d69972e45a60c26ad62268d80b3a49cce929e8a0dbece505fbbd35d597","schema_version":"1.0","event_id":"sha256:8cd1c7d69972e45a60c26ad62268d80b3a49cce929e8a0dbece505fbbd35d597"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/bundle.json","state_url":"https://pith.science/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/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":"2026-08-06T00:01:14Z","links":{"resolver":"https://pith.science/pith/AT4OJY6TWKOSMUBH3G67JKV3XX","bundle":"https://pith.science/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/bundle.json","state":"https://pith.science/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AT4OJY6TWKOSMUBH3G67JKV3XX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AT4OJY6TWKOSMUBH3G67JKV3XX","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":"3c17258ccdd58798cf76a7dfbeaf02e453bfc276fa2326508b6966530c2a7bff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:51:19Z","title_canon_sha256":"0ac4287a1a77977b1fabdf403dc9af859e0376fe5c172552a352505c94a88156"},"schema_version":"1.0","source":{"id":"2010.05901","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05901","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05901v2","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05901","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"AT4OJY6TWKOS","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_16","alias_value":"AT4OJY6TWKOSMUBH","created_at":"2026-07-05T01:45:31Z"},{"alias_kind":"pith_short_8","alias_value":"AT4OJY6T","created_at":"2026-07-05T01:45:31Z"}],"graph_snapshots":[{"event_id":"sha256:8cd1c7d69972e45a60c26ad62268d80b3a49cce929e8a0dbece505fbbd35d597","target":"graph","created_at":"2026-07-05T01:45:31Z","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/2010.05901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple reward functions. This framework has two phases. In the exploration phase, the agent collects trajectories by interacting with the environment without using any reward signal. In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions. We give a new efficient algorithm, \\textbf{S}taged \\textbf{S}ampling + \\textbf{T}runcated \\textbf{P}lanning (\\algoname), which interacts with the ","authors_text":"Simon S. Du, Xiangyang Ji, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:51:19Z","title":"Nearly Minimax Optimal Reward-free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05901","kind":"arxiv","version":2},"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":"sha256:512ac303e66308b2a596fac799689a0ee41cb5bdf210d9b1db13d2b6888e02cd","target":"record","created_at":"2026-07-05T01:45:31Z","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":"3c17258ccdd58798cf76a7dfbeaf02e453bfc276fa2326508b6966530c2a7bff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:51:19Z","title_canon_sha256":"0ac4287a1a77977b1fabdf403dc9af859e0376fe5c172552a352505c94a88156"},"schema_version":"1.0","source":{"id":"2010.05901","kind":"arxiv","version":2}},"canonical_sha256":"04f8e4e3d3b29d265027d9bdf4aabbbdd6f5a0c8052256768edebb8fe226a003","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04f8e4e3d3b29d265027d9bdf4aabbbdd6f5a0c8052256768edebb8fe226a003","first_computed_at":"2026-07-05T01:45:31.038331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:31.038331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tz86rjCNgSydY69j/MmIxgIaAqRSSC+of8U23Tu3Yeor5fUtf57i13njjwz5L9cpAWHwOUWertq7uawPZgRSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:31.038714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.05901","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:512ac303e66308b2a596fac799689a0ee41cb5bdf210d9b1db13d2b6888e02cd","sha256:8cd1c7d69972e45a60c26ad62268d80b3a49cce929e8a0dbece505fbbd35d597"],"state_sha256":"d0b43c51095ee76e55cbec27c06ef4de088762388e877f0b966d91f47da92d8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YeC4bGu5q3XQ0M1ASjdk14pqFBTfwm05R1brNIKMUCV/o8dvBCkTrt+A0fqdFv4F3XZ9duzYqN5bThFSodRkCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:01:14.077541Z","bundle_sha256":"070a1220465c438c5f0a6f03f6029696db1825603aa8a859fc3aa0b26b6710aa"}}