{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ACJODZ7YVVPSPIXWSSEVY5CT2K","short_pith_number":"pith:ACJODZ7Y","canonical_record":{"source":{"id":"2202.02790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T14:55:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30f030efdf3dd56e7521958ecb6512c1d490a0f48924dad0fcceeac97d5f07bc","abstract_canon_sha256":"92d704d98e5c1472c7d42e926186dc67c888c557061d69ce5b37c6c7ebda3f10"},"schema_version":"1.0"},"canonical_sha256":"0092e1e7f8ad5f27a2f694895c7453d291728813a9c0ec2e5f3756d4a5c80d52","source":{"kind":"arxiv","id":"2202.02790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.02790","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.02790v1","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02790","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"ACJODZ7YVVPS","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"ACJODZ7YVVPSPIXW","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"ACJODZ7Y","created_at":"2026-07-05T03:54:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ACJODZ7YVVPSPIXWSSEVY5CT2K","target":"record","payload":{"canonical_record":{"source":{"id":"2202.02790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T14:55:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30f030efdf3dd56e7521958ecb6512c1d490a0f48924dad0fcceeac97d5f07bc","abstract_canon_sha256":"92d704d98e5c1472c7d42e926186dc67c888c557061d69ce5b37c6c7ebda3f10"},"schema_version":"1.0"},"canonical_sha256":"0092e1e7f8ad5f27a2f694895c7453d291728813a9c0ec2e5f3756d4a5c80d52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:32.982054Z","signature_b64":"CkboMV5QSvCQ0z7CQs6p+x4BTtWQuHHiSl3RH1kH+ASrayWv4ZEf1row7MXeSheJvwMaTdcKdy//6UBm/3ZzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0092e1e7f8ad5f27a2f694895c7453d291728813a9c0ec2e5f3756d4a5c80d52","last_reissued_at":"2026-07-05T03:54:32.981649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:32.981649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.02790","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":"2026-07-05T03:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zsChv9FyRybfknl8Y977YrN8/ko4xgbgIyRMefOnFx2wiBSFj9RBCiMNsDgL4fDobr4Fiv3OmQlcPGXxd74jBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:43:33.126704Z"},"content_sha256":"0e83594b78a1d0e3a3cbca538caac0915813ad5ffc54ed9aeb77acbc88292f88","schema_version":"1.0","event_id":"sha256:0e83594b78a1d0e3a3cbca538caac0915813ad5ffc54ed9aeb77acbc88292f88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ACJODZ7YVVPSPIXWSSEVY5CT2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andreas Saelinger, Fabio Ferreira, Frank Hutter, Thomas Nierhoff","submitted_at":"2022-02-06T14:55:59Z","abstract_excerpt":"We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the SE, is able to solve the corresponding real environment. While an SE acts as a full proxy to a real environment by learning about its state dynamics and rewards, an RN is a partial proxy that learns to augment or replace rewards. We use bi-level optimization to evolve SEs and RNs: the inner loop trains the RL agent, and the outer loop trains the parameters o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02790","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/2202.02790/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":"2026-07-05T03:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3bInJAL88Wv0NfI4OTcZYKBuaHOBlyFtbwOjoFlPq2aI/WRWxB6zHjZZrA8lnM9VbFsO91My2T+jKpKWT7OTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:43:33.127090Z"},"content_sha256":"940970f691e7e4f4c4c24e6342838c14793f56dd776dd960cab2e95a664b8dcf","schema_version":"1.0","event_id":"sha256:940970f691e7e4f4c4c24e6342838c14793f56dd776dd960cab2e95a664b8dcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/bundle.json","state_url":"https://pith.science/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/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":"2026-07-09T01:43:33Z","links":{"resolver":"https://pith.science/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K","bundle":"https://pith.science/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/bundle.json","state":"https://pith.science/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACJODZ7YVVPSPIXWSSEVY5CT2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ACJODZ7YVVPSPIXWSSEVY5CT2K","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":"92d704d98e5c1472c7d42e926186dc67c888c557061d69ce5b37c6c7ebda3f10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T14:55:59Z","title_canon_sha256":"30f030efdf3dd56e7521958ecb6512c1d490a0f48924dad0fcceeac97d5f07bc"},"schema_version":"1.0","source":{"id":"2202.02790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.02790","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.02790v1","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02790","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"ACJODZ7YVVPS","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"ACJODZ7YVVPSPIXW","created_at":"2026-07-05T03:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"ACJODZ7Y","created_at":"2026-07-05T03:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:940970f691e7e4f4c4c24e6342838c14793f56dd776dd960cab2e95a664b8dcf","target":"graph","created_at":"2026-07-05T03:54:32Z","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/2202.02790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the SE, is able to solve the corresponding real environment. While an SE acts as a full proxy to a real environment by learning about its state dynamics and rewards, an RN is a partial proxy that learns to augment or replace rewards. We use bi-level optimization to evolve SEs and RNs: the inner loop trains the RL agent, and the outer loop trains the parameters o","authors_text":"Andreas Saelinger, Fabio Ferreira, Frank Hutter, Thomas Nierhoff","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T14:55:59Z","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02790","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":"sha256:0e83594b78a1d0e3a3cbca538caac0915813ad5ffc54ed9aeb77acbc88292f88","target":"record","created_at":"2026-07-05T03:54:32Z","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":"92d704d98e5c1472c7d42e926186dc67c888c557061d69ce5b37c6c7ebda3f10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T14:55:59Z","title_canon_sha256":"30f030efdf3dd56e7521958ecb6512c1d490a0f48924dad0fcceeac97d5f07bc"},"schema_version":"1.0","source":{"id":"2202.02790","kind":"arxiv","version":1}},"canonical_sha256":"0092e1e7f8ad5f27a2f694895c7453d291728813a9c0ec2e5f3756d4a5c80d52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0092e1e7f8ad5f27a2f694895c7453d291728813a9c0ec2e5f3756d4a5c80d52","first_computed_at":"2026-07-05T03:54:32.981649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:32.981649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CkboMV5QSvCQ0z7CQs6p+x4BTtWQuHHiSl3RH1kH+ASrayWv4ZEf1row7MXeSheJvwMaTdcKdy//6UBm/3ZzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:32.982054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.02790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e83594b78a1d0e3a3cbca538caac0915813ad5ffc54ed9aeb77acbc88292f88","sha256:940970f691e7e4f4c4c24e6342838c14793f56dd776dd960cab2e95a664b8dcf"],"state_sha256":"59ebd884a1cae4c364f382864a33f9794a97e18c5534b43cf67ca5be84988c99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yq7IXNoYN3YbTK2KhC+QUtnxUhGah7CQZUEb1cCqbcfPEOSBa6tH5FSZ1W7uxTBDGKc6PFQtDGZ+ZD4uHp9SCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:43:33.129274Z","bundle_sha256":"ba3c425fc2311bc5011b5f0f822e4b1a7d9c2224ed25a975f2f10c1edca5fca7"}}