{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TI7PGOHMNSC25UJM3ECX4WP3SV","short_pith_number":"pith:TI7PGOHM","canonical_record":{"source":{"id":"2001.05270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c9ab067bff038be3b294027ed4ceacc70768874baafc1e4439754ba72577b354","abstract_canon_sha256":"44b4451ccfa07a31ce9f515ee1874ce8f14b347a59af7f112c48b00af4483840"},"schema_version":"1.0"},"canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","source":{"kind":"arxiv","id":"2001.05270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05270","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05270v1","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05270","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"TI7PGOHMNSC2","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"TI7PGOHMNSC25UJM","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"TI7PGOHM","created_at":"2026-07-05T00:33:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TI7PGOHMNSC25UJM3ECX4WP3SV","target":"record","payload":{"canonical_record":{"source":{"id":"2001.05270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c9ab067bff038be3b294027ed4ceacc70768874baafc1e4439754ba72577b354","abstract_canon_sha256":"44b4451ccfa07a31ce9f515ee1874ce8f14b347a59af7f112c48b00af4483840"},"schema_version":"1.0"},"canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:40.679365Z","signature_b64":"dminlrDwb4HCDIuy7S3/W6Zp/8/OhpLaey9a0oCWeQ+AbvtQ5usrWVzRyx71GZQZ50GU8aov4hTT0AkzMRdGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","last_reissued_at":"2026-07-05T00:33:40.678790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:40.678790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.05270","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":"2026-07-05T00:33:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDHHfMacattMAyxBE+rYiceVzfjQEp73gawEP4hCJKqU7BWJPBr+rp5XPnr3YZqbAm5i3kSp+7zkGqeDbJSZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:59:44.809943Z"},"content_sha256":"eeb71093d9e2bc8b41f9d389bf77a1415637c1c50d0e1639d34c69f852f82db4","schema_version":"1.0","event_id":"sha256:eeb71093d9e2bc8b41f9d389bf77a1415637c1c50d0e1639d34c69f852f82db4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TI7PGOHMNSC25UJM3ECX4WP3SV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marco A. Wiering, Mario S. Holubar","submitted_at":"2020-01-15T12:30:57Z","abstract_excerpt":"In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05270","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/2001.05270/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":"2026-07-05T00:33:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cLqINXasIpxJgTKSezeA261VDvdiIifQgQcPSmV0+xcyi0Ypb4ggmhqJjVSkrhBRlxH2Izq9NIZKGPzZfTlVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:59:44.810776Z"},"content_sha256":"b0f39761af732b67b6c7b87b25603ecd8facb84ed8f4fe27653c18efbdc8ef55","schema_version":"1.0","event_id":"sha256:b0f39761af732b67b6c7b87b25603ecd8facb84ed8f4fe27653c18efbdc8ef55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/bundle.json","state_url":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/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":"2026-08-03T16:59:44Z","links":{"resolver":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV","bundle":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/bundle.json","state":"https://pith.science/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TI7PGOHMNSC25UJM3ECX4WP3SV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TI7PGOHMNSC25UJM3ECX4WP3SV","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":"44b4451ccfa07a31ce9f515ee1874ce8f14b347a59af7f112c48b00af4483840","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","title_canon_sha256":"c9ab067bff038be3b294027ed4ceacc70768874baafc1e4439754ba72577b354"},"schema_version":"1.0","source":{"id":"2001.05270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05270","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05270v1","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05270","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"TI7PGOHMNSC2","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"TI7PGOHMNSC25UJM","created_at":"2026-07-05T00:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"TI7PGOHM","created_at":"2026-07-05T00:33:40Z"}],"graph_snapshots":[{"event_id":"sha256:b0f39761af732b67b6c7b87b25603ecd8facb84ed8f4fe27653c18efbdc8ef55","target":"graph","created_at":"2026-07-05T00:33:40Z","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/2001.05270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay","authors_text":"Marco A. Wiering, Mario S. Holubar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","title":"Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05270","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:eeb71093d9e2bc8b41f9d389bf77a1415637c1c50d0e1639d34c69f852f82db4","target":"record","created_at":"2026-07-05T00:33:40Z","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":"44b4451ccfa07a31ce9f515ee1874ce8f14b347a59af7f112c48b00af4483840","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T12:30:57Z","title_canon_sha256":"c9ab067bff038be3b294027ed4ceacc70768874baafc1e4439754ba72577b354"},"schema_version":"1.0","source":{"id":"2001.05270","kind":"arxiv","version":1}},"canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a3ef338ec6c85aed12cd9057e59fb95625010f8d766fc4c4bf57104518dda25","first_computed_at":"2026-07-05T00:33:40.678790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:40.678790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dminlrDwb4HCDIuy7S3/W6Zp/8/OhpLaey9a0oCWeQ+AbvtQ5usrWVzRyx71GZQZ50GU8aov4hTT0AkzMRdGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:40.679365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb71093d9e2bc8b41f9d389bf77a1415637c1c50d0e1639d34c69f852f82db4","sha256:b0f39761af732b67b6c7b87b25603ecd8facb84ed8f4fe27653c18efbdc8ef55"],"state_sha256":"61fb5e8642c8da6946a52429803550a9c7d5cdc4feb74ded741a2f7cfae9a651"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7K/KxsAk6WQF5QLe5ZyhnntCGqTIlaccIyH0fxOGmLDOJGjQYxOmVrrJ8TQtMKj9iSrylzPuY++wJbgq3ONBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:59:44.816797Z","bundle_sha256":"b9e5efb2f4e3e140dad16e895d2080de098df7035799aa5ace1e6dd5895f2cd0"}}