{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EQUZ34NJ5P4SDEJ644DP7NWVDM","short_pith_number":"pith:EQUZ34NJ","canonical_record":{"source":{"id":"2106.08918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T16:18:20Z","cross_cats_sorted":["cs.NE","cs.SY","eess.SY"],"title_canon_sha256":"0386bd3cc5776f67afb8e41967afa81dfc4bb03c6df2309812cb0f1f4099fc5e","abstract_canon_sha256":"7cc0a92debf00f5cbd66bf4694111f2ec3fca74a593d33ac62f7083cd1a02998"},"schema_version":"1.0"},"canonical_sha256":"24299df1a9ebf921913ee706ffb6d51b1887f569c02e25bdac442edafd2ae102","source":{"kind":"arxiv","id":"2106.08918","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08918","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08918v2","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08918","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"EQUZ34NJ5P4S","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"EQUZ34NJ5P4SDEJ6","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"EQUZ34NJ","created_at":"2026-07-05T03:24:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EQUZ34NJ5P4SDEJ644DP7NWVDM","target":"record","payload":{"canonical_record":{"source":{"id":"2106.08918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T16:18:20Z","cross_cats_sorted":["cs.NE","cs.SY","eess.SY"],"title_canon_sha256":"0386bd3cc5776f67afb8e41967afa81dfc4bb03c6df2309812cb0f1f4099fc5e","abstract_canon_sha256":"7cc0a92debf00f5cbd66bf4694111f2ec3fca74a593d33ac62f7083cd1a02998"},"schema_version":"1.0"},"canonical_sha256":"24299df1a9ebf921913ee706ffb6d51b1887f569c02e25bdac442edafd2ae102","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:57.760969Z","signature_b64":"46U9UAFri6ETUuJeFBsPMuf2X4XzcVmccYFwue+zYKc/KcNh2pCOX6dlvZtNXoi97kvsv6UqUyLqqmBNZ3yoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24299df1a9ebf921913ee706ffb6d51b1887f569c02e25bdac442edafd2ae102","last_reissued_at":"2026-07-05T03:24:57.760547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:57.760547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.08918","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERfev42DdjgnzjUn/H0B+s6auhe/vZIlIUAxY8UDJlfMQWQj9XygrYOWI3zohGZtOc5dbVa0WIRIuuwuE7uDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T16:42:46.168841Z"},"content_sha256":"870b6e3f326961f879803d7945005658f9cd77c334b76854409494ddb9a16ef0","schema_version":"1.0","event_id":"sha256:870b6e3f326961f879803d7945005658f9cd77c334b76854409494ddb9a16ef0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EQUZ34NJ5P4SDEJ644DP7NWVDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Automatic Actor-Critic Solutions to Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Jake Grigsby, Jin Yong Yoo, Yanjun Qi","submitted_at":"2021-06-16T16:18:20Z","abstract_excerpt":"Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks. However, these algorithms rely on a number of design tricks and hyperparameters, making their application to new domains difficult and computationally expensive. This paper creates an evolutionary approach that automatically tunes these design decisions and eliminates the RL-specific hyperparameters from the Soft Actor-Critic algorithm. Our design is sample efficient and provides practical advantages over baseline approaches, including improved exploration, generalization over multiple con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08918","kind":"arxiv","version":2},"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/2106.08918/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":"2026-07-05T03:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iaK9Dq3q4urq4dSnBtgYXw1q7mYc3Q+dSgsTMil37ucyuaPPOInTSdPjojGe6jWEJxvuk8mRrVhGizNyLI5dBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T16:42:46.169225Z"},"content_sha256":"b58a9a7abf066797a534923b7e1f9c7b8b62c45230c5169cc1a55a4deaa84045","schema_version":"1.0","event_id":"sha256:b58a9a7abf066797a534923b7e1f9c7b8b62c45230c5169cc1a55a4deaa84045"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/bundle.json","state_url":"https://pith.science/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/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":"2026-07-24T16:42:46Z","links":{"resolver":"https://pith.science/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM","bundle":"https://pith.science/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/bundle.json","state":"https://pith.science/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQUZ34NJ5P4SDEJ644DP7NWVDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EQUZ34NJ5P4SDEJ644DP7NWVDM","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":"7cc0a92debf00f5cbd66bf4694111f2ec3fca74a593d33ac62f7083cd1a02998","cross_cats_sorted":["cs.NE","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T16:18:20Z","title_canon_sha256":"0386bd3cc5776f67afb8e41967afa81dfc4bb03c6df2309812cb0f1f4099fc5e"},"schema_version":"1.0","source":{"id":"2106.08918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08918","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08918v2","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08918","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"EQUZ34NJ5P4S","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"EQUZ34NJ5P4SDEJ6","created_at":"2026-07-05T03:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"EQUZ34NJ","created_at":"2026-07-05T03:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:b58a9a7abf066797a534923b7e1f9c7b8b62c45230c5169cc1a55a4deaa84045","target":"graph","created_at":"2026-07-05T03:24:57Z","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/2106.08918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks. However, these algorithms rely on a number of design tricks and hyperparameters, making their application to new domains difficult and computationally expensive. This paper creates an evolutionary approach that automatically tunes these design decisions and eliminates the RL-specific hyperparameters from the Soft Actor-Critic algorithm. Our design is sample efficient and provides practical advantages over baseline approaches, including improved exploration, generalization over multiple con","authors_text":"Jake Grigsby, Jin Yong Yoo, Yanjun Qi","cross_cats":["cs.NE","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T16:18:20Z","title":"Towards Automatic Actor-Critic Solutions to Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08918","kind":"arxiv","version":2},"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":"sha256:870b6e3f326961f879803d7945005658f9cd77c334b76854409494ddb9a16ef0","target":"record","created_at":"2026-07-05T03:24:57Z","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":"7cc0a92debf00f5cbd66bf4694111f2ec3fca74a593d33ac62f7083cd1a02998","cross_cats_sorted":["cs.NE","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T16:18:20Z","title_canon_sha256":"0386bd3cc5776f67afb8e41967afa81dfc4bb03c6df2309812cb0f1f4099fc5e"},"schema_version":"1.0","source":{"id":"2106.08918","kind":"arxiv","version":2}},"canonical_sha256":"24299df1a9ebf921913ee706ffb6d51b1887f569c02e25bdac442edafd2ae102","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24299df1a9ebf921913ee706ffb6d51b1887f569c02e25bdac442edafd2ae102","first_computed_at":"2026-07-05T03:24:57.760547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:57.760547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46U9UAFri6ETUuJeFBsPMuf2X4XzcVmccYFwue+zYKc/KcNh2pCOX6dlvZtNXoi97kvsv6UqUyLqqmBNZ3yoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:57.760969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:870b6e3f326961f879803d7945005658f9cd77c334b76854409494ddb9a16ef0","sha256:b58a9a7abf066797a534923b7e1f9c7b8b62c45230c5169cc1a55a4deaa84045"],"state_sha256":"f668b4536366c30df62556356a4afaeb8a6dbfb94a145bdbcaf933f8da5616b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YImO5JhvOOI5cAdCesnVqS2GiVKLz0CiTctJsgueiiTWJhCar+nUq9JFa11BKXwktLMJ4sHAipJt3X+ux7IfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T16:42:46.171461Z","bundle_sha256":"3112e964a4657ca5e30fd15b7996374c14d9394f3af389f82aed3ea169773648"}}