{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4X5FSUAPBCFSRPJJSCEIOZQ7QO","short_pith_number":"pith:4X5FSUAP","schema_version":"1.0","canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","source":{"kind":"arxiv","id":"1709.09069","version":1},"attestation_state":"computed","paper":{"title":"MDP environments for the OpenAI Gym","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Kirsch","submitted_at":"2017-09-26T14:52:23Z","abstract_excerpt":"The OpenAI Gym provides researchers and enthusiasts with simple to use environments for reinforcement learning. Even the simplest environment have a level of complexity that can obfuscate the inner workings of RL approaches and make debugging difficult. This whitepaper describes a Python framework that makes it very easy to create simple Markov-Decision-Process environments programmatically by specifying state transitions and rewards of deterministic and non-deterministic MDPs in a domain-specific language in Python. It then presents results and visualizations created with this MDP framework."},"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":"1709.09069","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-26T14:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"19285c8812a40e6f168e431c33b083ab66b05bf59757e9fa750055e064057fc9","abstract_canon_sha256":"c0c1f481c4b9907d5a5c76c891a5518afd4e991242cc6db8620715288c0f9485"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:21.247266Z","signature_b64":"s1KGPdUL1qrMHlplg7T2ucQhhhuux4Vgl8iOreX/Jp8QNoTs+AeDcblKl8jwjKJbut9HuxasDThiJqIpzGqBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","last_reissued_at":"2026-05-18T00:34:21.246738Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:21.246738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDP environments for the OpenAI Gym","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Kirsch","submitted_at":"2017-09-26T14:52:23Z","abstract_excerpt":"The OpenAI Gym provides researchers and enthusiasts with simple to use environments for reinforcement learning. Even the simplest environment have a level of complexity that can obfuscate the inner workings of RL approaches and make debugging difficult. This whitepaper describes a Python framework that makes it very easy to create simple Markov-Decision-Process environments programmatically by specifying state transitions and rewards of deterministic and non-deterministic MDPs in a domain-specific language in Python. It then presents results and visualizations created with this MDP framework."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09069","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":""},"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":"1709.09069","created_at":"2026-05-18T00:34:21.246836+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.09069v1","created_at":"2026-05-18T00:34:21.246836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09069","created_at":"2026-05-18T00:34:21.246836+00:00"},{"alias_kind":"pith_short_12","alias_value":"4X5FSUAPBCFS","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4X5FSUAPBCFSRPJJ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4X5FSUAP","created_at":"2026-05-18T12:31:00.734936+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/4X5FSUAPBCFSRPJJSCEIOZQ7QO","json":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO.json","graph_json":"https://pith.science/api/pith-number/4X5FSUAPBCFSRPJJSCEIOZQ7QO/graph.json","events_json":"https://pith.science/api/pith-number/4X5FSUAPBCFSRPJJSCEIOZQ7QO/events.json","paper":"https://pith.science/paper/4X5FSUAP"},"agent_actions":{"view_html":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO","download_json":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO.json","view_paper":"https://pith.science/paper/4X5FSUAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.09069&json=true","fetch_graph":"https://pith.science/api/pith-number/4X5FSUAPBCFSRPJJSCEIOZQ7QO/graph.json","fetch_events":"https://pith.science/api/pith-number/4X5FSUAPBCFSRPJJSCEIOZQ7QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/action/storage_attestation","attest_author":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/action/author_attestation","sign_citation":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/action/citation_signature","submit_replication":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/action/replication_record"}},"created_at":"2026-05-18T00:34:21.246836+00:00","updated_at":"2026-05-18T00:34:21.246836+00:00"}