{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4X5FSUAPBCFSRPJJSCEIOZQ7QO","short_pith_number":"pith:4X5FSUAP","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"},"canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","source":{"kind":"arxiv","id":"1709.09069","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09069","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09069v1","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09069","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"4X5FSUAPBCFS","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4X5FSUAPBCFSRPJJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4X5FSUAP","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4X5FSUAPBCFSRPJJSCEIOZQ7QO","target":"record","payload":{"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"},"canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","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"},"source_kind":"arxiv","source_id":"1709.09069","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":"2026-05-18T00:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3kZnP4RibaJceRIuCeIIRpDJ7Fbmnu76qsTTmvMJciK7yJMT/kzD//H8lXNyLgJuR0BjOlqioD7fTp64kwKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T02:28:29.872172Z"},"content_sha256":"78156a0aaf2454df843214457b4256be3bdf57026d40f5956aafba594a8d715e","schema_version":"1.0","event_id":"sha256:78156a0aaf2454df843214457b4256be3bdf57026d40f5956aafba594a8d715e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4X5FSUAPBCFSRPJJSCEIOZQ7QO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNgRSigxXIyrYLGGKEII3Jwy2NBo/86iGfeI+mBxy23QjBZJKnEt7Xl+BooIVij8AZPLW7gb+sUcvhEzrO9sAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T02:28:29.872536Z"},"content_sha256":"d45d343b8f3ae93066b038743d6d95b384fae74da9fecc1993e8ce241d5dd1f6","schema_version":"1.0","event_id":"sha256:d45d343b8f3ae93066b038743d6d95b384fae74da9fecc1993e8ce241d5dd1f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/bundle.json","state_url":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/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":"2026-07-01T02:28:29Z","links":{"resolver":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO","bundle":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/bundle.json","state":"https://pith.science/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4X5FSUAPBCFSRPJJSCEIOZQ7QO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4X5FSUAPBCFSRPJJSCEIOZQ7QO","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":"c0c1f481c4b9907d5a5c76c891a5518afd4e991242cc6db8620715288c0f9485","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-26T14:52:23Z","title_canon_sha256":"19285c8812a40e6f168e431c33b083ab66b05bf59757e9fa750055e064057fc9"},"schema_version":"1.0","source":{"id":"1709.09069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09069","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09069v1","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09069","created_at":"2026-05-18T00:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"4X5FSUAPBCFS","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4X5FSUAPBCFSRPJJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4X5FSUAP","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:d45d343b8f3ae93066b038743d6d95b384fae74da9fecc1993e8ce241d5dd1f6","target":"graph","created_at":"2026-05-18T00:34:21Z","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"},"paper":{"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.","authors_text":"Andreas Kirsch","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-26T14:52:23Z","title":"MDP environments for the OpenAI Gym"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09069","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":"sha256:78156a0aaf2454df843214457b4256be3bdf57026d40f5956aafba594a8d715e","target":"record","created_at":"2026-05-18T00:34:21Z","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":"c0c1f481c4b9907d5a5c76c891a5518afd4e991242cc6db8620715288c0f9485","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-26T14:52:23Z","title_canon_sha256":"19285c8812a40e6f168e431c33b083ab66b05bf59757e9fa750055e064057fc9"},"schema_version":"1.0","source":{"id":"1709.09069","kind":"arxiv","version":1}},"canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5fa59500f088b28bd29908887661f83a390f8171b01aa18c08aea5b17e1973a","first_computed_at":"2026-05-18T00:34:21.246738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:21.246738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s1KGPdUL1qrMHlplg7T2ucQhhhuux4Vgl8iOreX/Jp8QNoTs+AeDcblKl8jwjKJbut9HuxasDThiJqIpzGqBAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:21.247266Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.09069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78156a0aaf2454df843214457b4256be3bdf57026d40f5956aafba594a8d715e","sha256:d45d343b8f3ae93066b038743d6d95b384fae74da9fecc1993e8ce241d5dd1f6"],"state_sha256":"a7efe6a6c646f3fc482b67e3fa55db2d8b75f7f43b43a28b3d2fe92a5e052721"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFm7cs/3th95sCqWaE2KU5O313c4p79F6h6nmT19Zh2SVkTRo89Pd67xlUw5VcpkgOlDleSz0kmko++1XtdZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T02:28:29.874475Z","bundle_sha256":"42e64c3e7bad4998665bad1fd3e2dcf2f167f8f2146e03ba9ec4a52edb5bc28b"}}