{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RUDPUMDWAJGFYHJ44G6RF2L43A","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":"105a57b0aefa47d6586c607a5e7d1365a0bc8961183200d3aaf4d424e2c9159b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-10-18T01:10:37Z","title_canon_sha256":"0b66a6078a6a5f5da4058772b48b25d660b6bcd10c8af847a46b8230c994e391"},"schema_version":"1.0","source":{"id":"1710.06542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06542","created_at":"2026-05-18T00:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06542v1","created_at":"2026-05-18T00:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06542","created_at":"2026-05-18T00:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"RUDPUMDWAJGF","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RUDPUMDWAJGFYHJ4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RUDPUMDW","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:ed034877bf736d29df014223548c5d871f6bb9f8308fe726f73389784d36c277","target":"graph","created_at":"2026-05-18T00:32:33Z","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":"Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which has sparked significant interest in learning control policies using a physics simulator. While several recent works have shown promising results in transferring policies trained in simulation to the real world, they often do not fully utilize the advantage of working with a simulator. In this work, we exploit the full state observability in the simulator to tr","authors_text":"Lerrel Pinto, Marcin Andrychowicz, Peter Welinder, Pieter Abbeel, Wojciech Zaremba","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-10-18T01:10:37Z","title":"Asymmetric Actor Critic for Image-Based Robot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06542","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":"sha256:795b4092e50b262b8e96da2a343b0e9ddeb2a0a9c252e059a6d5e352c3047012","target":"record","created_at":"2026-05-18T00:32:33Z","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":"105a57b0aefa47d6586c607a5e7d1365a0bc8961183200d3aaf4d424e2c9159b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-10-18T01:10:37Z","title_canon_sha256":"0b66a6078a6a5f5da4058772b48b25d660b6bcd10c8af847a46b8230c994e391"},"schema_version":"1.0","source":{"id":"1710.06542","kind":"arxiv","version":1}},"canonical_sha256":"8d06fa3076024c5c1d3ce1bd12e97cd80d21bfbc058670db5eb90db984623411","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d06fa3076024c5c1d3ce1bd12e97cd80d21bfbc058670db5eb90db984623411","first_computed_at":"2026-05-18T00:32:33.413636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:33.413636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Crsylmpql2LXKdoTExDUChg95t+DQFFjDMbezwuCzYtpNVgxGX0JB0u1+UE66TLrkIRN2P8kIFMIXJXcmNgTAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:33.414456Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.06542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:795b4092e50b262b8e96da2a343b0e9ddeb2a0a9c252e059a6d5e352c3047012","sha256:ed034877bf736d29df014223548c5d871f6bb9f8308fe726f73389784d36c277"],"state_sha256":"5d98b58f4500b7d6befd0fc7b6a5dc76552069327ca03b9489e15201d75b201d"}