{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VMLRZGTXD46NZKQMB2NOD2DM34","short_pith_number":"pith:VMLRZGTX","schema_version":"1.0","canonical_sha256":"ab171c9a771f3cdcaa0c0e9ae1e86cdf2d1fa545456a3df1ac21c216cd7e2c69","source":{"kind":"arxiv","id":"2312.03290","version":1},"attestation_state":"computed","paper":{"title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bo Jin, Chuyun Shen, Hongyuan Zha, Junjie Sheng, Wenhao Li, Xiangfeng Wang, Yun Hua, Zixiao Huang","submitted_at":"2023-12-06T04:48:26Z","abstract_excerpt":"The formidable capacity for zero- or few-shot decision-making in language agents encourages us to pose a compelling question: Can language agents be alternatives to PPO agents in traditional sequential decision-making tasks? To investigate this, we first take environments collected in OpenAI Gym as our testbeds and ground them to textual environments that construct the TextGym simulator. This allows for straightforward and efficient comparisons between PPO agents and language agents, given the widespread adoption of OpenAI Gym. To ensure a fair and effective benchmarking, we introduce $5$ leve"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.03290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-06T04:48:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aa00791aa3175e0a6b54279c3b70bb8556acfe450ce70d4dc8a1f3c7adb8e114","abstract_canon_sha256":"4b47d8c79bc940451bc626c7aa8608ed5f9063136abaad3ea654b6d26998958d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:01.509814Z","signature_b64":"ij+phJSZ06ijajoqjc3t/uaqmfpwn0TfimsWLzdKBXiilKu9EnwzlzMC6hj335MbA1mdmRBg3bnU7BiZfqY2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab171c9a771f3cdcaa0c0e9ae1e86cdf2d1fa545456a3df1ac21c216cd7e2c69","last_reissued_at":"2026-07-05T07:21:01.509341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:01.509341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bo Jin, Chuyun Shen, Hongyuan Zha, Junjie Sheng, Wenhao Li, Xiangfeng Wang, Yun Hua, Zixiao Huang","submitted_at":"2023-12-06T04:48:26Z","abstract_excerpt":"The formidable capacity for zero- or few-shot decision-making in language agents encourages us to pose a compelling question: Can language agents be alternatives to PPO agents in traditional sequential decision-making tasks? To investigate this, we first take environments collected in OpenAI Gym as our testbeds and ground them to textual environments that construct the TextGym simulator. This allows for straightforward and efficient comparisons between PPO agents and language agents, given the widespread adoption of OpenAI Gym. To ensure a fair and effective benchmarking, we introduce $5$ leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03290","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/2312.03290/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.03290","created_at":"2026-07-05T07:21:01.509405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03290v1","created_at":"2026-07-05T07:21:01.509405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03290","created_at":"2026-07-05T07:21:01.509405+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMLRZGTXD46N","created_at":"2026-07-05T07:21:01.509405+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMLRZGTXD46NZKQM","created_at":"2026-07-05T07:21:01.509405+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMLRZGTX","created_at":"2026-07-05T07:21:01.509405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34","json":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34.json","graph_json":"https://pith.science/api/pith-number/VMLRZGTXD46NZKQMB2NOD2DM34/graph.json","events_json":"https://pith.science/api/pith-number/VMLRZGTXD46NZKQMB2NOD2DM34/events.json","paper":"https://pith.science/paper/VMLRZGTX"},"agent_actions":{"view_html":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34","download_json":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34.json","view_paper":"https://pith.science/paper/VMLRZGTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03290&json=true","fetch_graph":"https://pith.science/api/pith-number/VMLRZGTXD46NZKQMB2NOD2DM34/graph.json","fetch_events":"https://pith.science/api/pith-number/VMLRZGTXD46NZKQMB2NOD2DM34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34/action/storage_attestation","attest_author":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34/action/author_attestation","sign_citation":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34/action/citation_signature","submit_replication":"https://pith.science/pith/VMLRZGTXD46NZKQMB2NOD2DM34/action/replication_record"}},"created_at":"2026-07-05T07:21:01.509405+00:00","updated_at":"2026-07-05T07:21:01.509405+00:00"}