{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GDDWJC2DAPCNB676TA3NYCOKYA","short_pith_number":"pith:GDDWJC2D","canonical_record":{"source":{"id":"2208.07587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T08:00:43Z","cross_cats_sorted":[],"title_canon_sha256":"b8bcdd18858957d1e9f3fdd10fca2b3ece938e0bc3850f0dcc485735b1597561","abstract_canon_sha256":"f1404e6196ac5cfe662617458fbd33de66e373e04366ce80d68f2334067c3b21"},"schema_version":"1.0"},"canonical_sha256":"30c7648b4303c4d0fbfe9836dc09cac02804155f86dcaca3d6f0a8905b6ca54c","source":{"kind":"arxiv","id":"2208.07587","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07587","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07587v3","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07587","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_12","alias_value":"GDDWJC2DAPCN","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_16","alias_value":"GDDWJC2DAPCNB676","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_8","alias_value":"GDDWJC2D","created_at":"2026-07-05T04:51:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GDDWJC2DAPCNB676TA3NYCOKYA","target":"record","payload":{"canonical_record":{"source":{"id":"2208.07587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T08:00:43Z","cross_cats_sorted":[],"title_canon_sha256":"b8bcdd18858957d1e9f3fdd10fca2b3ece938e0bc3850f0dcc485735b1597561","abstract_canon_sha256":"f1404e6196ac5cfe662617458fbd33de66e373e04366ce80d68f2334067c3b21"},"schema_version":"1.0"},"canonical_sha256":"30c7648b4303c4d0fbfe9836dc09cac02804155f86dcaca3d6f0a8905b6ca54c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:24.965663Z","signature_b64":"9Liuwl8ayRg5XOQCElVeBAHwFhv+HMy7kcstnYSQthxXfBKIMZkZBo0aOwNCK8IKiQbfXG9L3fd2A+MCt+P+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c7648b4303c4d0fbfe9836dc09cac02804155f86dcaca3d6f0a8905b6ca54c","last_reissued_at":"2026-07-05T04:51:24.965282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:24.965282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.07587","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:51:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/8vWaYzym3t1x7OmnAXyp9YLdYR/Q2Buh0ymf94sutUqkSuFsDr9MvDbSfALKMmhXGF2aFuBRZlvhwER6PYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:16:28.533174Z"},"content_sha256":"e03afe76d84fef756b774c129267c3c0be1d0ea5abf832ae47f82874f80798b0","schema_version":"1.0","event_id":"sha256:e03afe76d84fef756b774c129267c3c0be1d0ea5abf832ae47f82874f80798b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GDDWJC2DAPCNB676TA3NYCOKYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Reinforcement Learning Work on Swimmer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonin Raffin, Coline Lacoux, Ma\\\"el Franceschetti, Olivier Sigaud, Ryan Ohouens","submitted_at":"2022-08-16T08:00:43Z","abstract_excerpt":"The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy search methods such as genetic algorithms or evolution strategies. A lot of these papers report poor performance on SWIMMER from RL methods and much better performance from direct policy search methods. In this technical report we show that the low performance of RL methods on SWIMMER simply comes from the inadequate tuning of an important hyper-parameter, the discount factor. Furthermore we show that, by setting this hyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07587","kind":"arxiv","version":3},"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/2208.07587/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":"2026-07-05T04:51:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GNsfvYwdVBVov75B1F+taQXxfeKgoGaD2XspXHyqXjh5HUn5JgaVAbx9ApWf7kBNSmohBNynPXIfhzWPJHvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:16:28.533793Z"},"content_sha256":"d4b85f2aec670917d87c23458a235159a5c2cf381f403bc0bf715bcbb69d5bbc","schema_version":"1.0","event_id":"sha256:d4b85f2aec670917d87c23458a235159a5c2cf381f403bc0bf715bcbb69d5bbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDDWJC2DAPCNB676TA3NYCOKYA/bundle.json","state_url":"https://pith.science/pith/GDDWJC2DAPCNB676TA3NYCOKYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDDWJC2DAPCNB676TA3NYCOKYA/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":"2026-08-16T19:16:28Z","links":{"resolver":"https://pith.science/pith/GDDWJC2DAPCNB676TA3NYCOKYA","bundle":"https://pith.science/pith/GDDWJC2DAPCNB676TA3NYCOKYA/bundle.json","state":"https://pith.science/pith/GDDWJC2DAPCNB676TA3NYCOKYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDDWJC2DAPCNB676TA3NYCOKYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GDDWJC2DAPCNB676TA3NYCOKYA","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":"f1404e6196ac5cfe662617458fbd33de66e373e04366ce80d68f2334067c3b21","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T08:00:43Z","title_canon_sha256":"b8bcdd18858957d1e9f3fdd10fca2b3ece938e0bc3850f0dcc485735b1597561"},"schema_version":"1.0","source":{"id":"2208.07587","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07587","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07587v3","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07587","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_12","alias_value":"GDDWJC2DAPCN","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_16","alias_value":"GDDWJC2DAPCNB676","created_at":"2026-07-05T04:51:24Z"},{"alias_kind":"pith_short_8","alias_value":"GDDWJC2D","created_at":"2026-07-05T04:51:24Z"}],"graph_snapshots":[{"event_id":"sha256:d4b85f2aec670917d87c23458a235159a5c2cf381f403bc0bf715bcbb69d5bbc","target":"graph","created_at":"2026-07-05T04:51:24Z","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/2208.07587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy search methods such as genetic algorithms or evolution strategies. A lot of these papers report poor performance on SWIMMER from RL methods and much better performance from direct policy search methods. In this technical report we show that the low performance of RL methods on SWIMMER simply comes from the inadequate tuning of an important hyper-parameter, the discount factor. Furthermore we show that, by setting this hyp","authors_text":"Antonin Raffin, Coline Lacoux, Ma\\\"el Franceschetti, Olivier Sigaud, Ryan Ohouens","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T08:00:43Z","title":"Making Reinforcement Learning Work on Swimmer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07587","kind":"arxiv","version":3},"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:e03afe76d84fef756b774c129267c3c0be1d0ea5abf832ae47f82874f80798b0","target":"record","created_at":"2026-07-05T04:51:24Z","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":"f1404e6196ac5cfe662617458fbd33de66e373e04366ce80d68f2334067c3b21","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T08:00:43Z","title_canon_sha256":"b8bcdd18858957d1e9f3fdd10fca2b3ece938e0bc3850f0dcc485735b1597561"},"schema_version":"1.0","source":{"id":"2208.07587","kind":"arxiv","version":3}},"canonical_sha256":"30c7648b4303c4d0fbfe9836dc09cac02804155f86dcaca3d6f0a8905b6ca54c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c7648b4303c4d0fbfe9836dc09cac02804155f86dcaca3d6f0a8905b6ca54c","first_computed_at":"2026-07-05T04:51:24.965282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:24.965282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Liuwl8ayRg5XOQCElVeBAHwFhv+HMy7kcstnYSQthxXfBKIMZkZBo0aOwNCK8IKiQbfXG9L3fd2A+MCt+P+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:24.965663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.07587","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e03afe76d84fef756b774c129267c3c0be1d0ea5abf832ae47f82874f80798b0","sha256:d4b85f2aec670917d87c23458a235159a5c2cf381f403bc0bf715bcbb69d5bbc"],"state_sha256":"24435568c9724f1f28293074625ab23d68892314067cd94026509b3c36acfd24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xPTZRoX/JVSymB/xmo1n+TpEB9NbfOBUtvw/txDMMApv/PJ0M7jmsjyS+7ruvfXsMax2W7gbtsxfK2E9aw8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:16:28.540404Z","bundle_sha256":"31b3e4884cd3a2d4f89105b73eec01f39c8d2dbf94fd5232a6cd0b3c2e270f94"}}