{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:D4HKML3YDOIXN6XWKR75C7CAY4","short_pith_number":"pith:D4HKML3Y","canonical_record":{"source":{"id":"1802.09464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T17:20:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"32c394b9b40b1df6913ca2c3b8562361ab6e551c46cb21bf90a55d1f59c37b69","abstract_canon_sha256":"022518338fd42e31f0c03e87fbedf4e57595cae7a5ff34b74abf17fba44affb7"},"schema_version":"1.0"},"canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","source":{"kind":"arxiv","id":"1802.09464","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09464","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09464v2","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09464","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"D4HKML3YDOIX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D4HKML3YDOIXN6XW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D4HKML3Y","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:D4HKML3YDOIXN6XWKR75C7CAY4","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T17:20:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"32c394b9b40b1df6913ca2c3b8562361ab6e551c46cb21bf90a55d1f59c37b69","abstract_canon_sha256":"022518338fd42e31f0c03e87fbedf4e57595cae7a5ff34b74abf17fba44affb7"},"schema_version":"1.0"},"canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:34.090794Z","signature_b64":"GCJ/JTXLJjA7Q2PF7saD+04jl3JAMyudoBY4aXWFXOnmGmwRCKPdlcINvNZQfAcB+kH+gkWdmLADfaC0afQeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","last_reissued_at":"2026-05-18T00:21:34.090153Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:34.090153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09464","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":"2026-05-18T00:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KEaCJuAQMcvSmO9LNDsW+gmU3BLh+n0xtEVThayMWkemcJoctnQJAuD9fxLqu5uwvvCv0/mxVRCR4BSC6RLdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:39:28.636845Z"},"content_sha256":"4a840e37b90280633bb040ce40d99449a8cb19fa6bc6f1f01bb49e9ba3cafac0","schema_version":"1.0","event_id":"sha256:4a840e37b90280633bb040ce40d99449a8cb19fa6bc6f1f01bb49e9ba3cafac0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:D4HKML3YDOIXN6XWKR75C7CAY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Ray, Bob McGrew, Bowen Baker, Glenn Powell, Jonas Schneider, Josh Tobin, Maciek Chociej, Marcin Andrychowicz, Matthias Plappert, Peter Welinder, Vikash Kumar, Wojciech Zaremba","submitted_at":"2018-02-26T17:20:14Z","abstract_excerpt":"The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input.\n  The second part of the paper presents a set of concrete research ideas for improving RL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09464","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":""},"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":"2026-05-18T00:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kOTQa5fglD86BIOCiF73clsb5nK4zcUPDQafBeoFir2T4Uoa1DNcYkVRmLdfHgSPJ0eqR2cCVOmOyJuB43eEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:39:28.637200Z"},"content_sha256":"7615c383bc9e2dd4ac8a2c688a3b30ca04558b97ca7afe0d84f0d3cede125ebf","schema_version":"1.0","event_id":"sha256:7615c383bc9e2dd4ac8a2c688a3b30ca04558b97ca7afe0d84f0d3cede125ebf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/bundle.json","state_url":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4HKML3YDOIXN6XWKR75C7CAY4/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":"2026-06-03T02:39:28Z","links":{"resolver":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4","bundle":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/bundle.json","state":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4HKML3YDOIXN6XWKR75C7CAY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:D4HKML3YDOIXN6XWKR75C7CAY4","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":"022518338fd42e31f0c03e87fbedf4e57595cae7a5ff34b74abf17fba44affb7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T17:20:14Z","title_canon_sha256":"32c394b9b40b1df6913ca2c3b8562361ab6e551c46cb21bf90a55d1f59c37b69"},"schema_version":"1.0","source":{"id":"1802.09464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09464","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09464v2","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09464","created_at":"2026-05-18T00:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"D4HKML3YDOIX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D4HKML3YDOIXN6XW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D4HKML3Y","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:7615c383bc9e2dd4ac8a2c688a3b30ca04558b97ca7afe0d84f0d3cede125ebf","target":"graph","created_at":"2026-05-18T00:21:34Z","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":"The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input.\n  The second part of the paper presents a set of concrete research ideas for improving RL","authors_text":"Alex Ray, Bob McGrew, Bowen Baker, Glenn Powell, Jonas Schneider, Josh Tobin, Maciek Chociej, Marcin Andrychowicz, Matthias Plappert, Peter Welinder, Vikash Kumar, Wojciech Zaremba","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T17:20:14Z","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09464","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":"sha256:4a840e37b90280633bb040ce40d99449a8cb19fa6bc6f1f01bb49e9ba3cafac0","target":"record","created_at":"2026-05-18T00:21:34Z","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":"022518338fd42e31f0c03e87fbedf4e57595cae7a5ff34b74abf17fba44affb7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T17:20:14Z","title_canon_sha256":"32c394b9b40b1df6913ca2c3b8562361ab6e551c46cb21bf90a55d1f59c37b69"},"schema_version":"1.0","source":{"id":"1802.09464","kind":"arxiv","version":2}},"canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","first_computed_at":"2026-05-18T00:21:34.090153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:34.090153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GCJ/JTXLJjA7Q2PF7saD+04jl3JAMyudoBY4aXWFXOnmGmwRCKPdlcINvNZQfAcB+kH+gkWdmLADfaC0afQeAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:34.090794Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a840e37b90280633bb040ce40d99449a8cb19fa6bc6f1f01bb49e9ba3cafac0","sha256:7615c383bc9e2dd4ac8a2c688a3b30ca04558b97ca7afe0d84f0d3cede125ebf"],"state_sha256":"f07284327e661aaa825cefae4b1f762ce4a232d372f25bcd08b14838b0098353"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PX6+4pct6LUTd2z81PB/XRPuWVFEJlY6cjWQn4XsbH+movnctd6fEMfuRd0bTsReFk4NW2cCkf333GFgaaR8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:39:28.639190Z","bundle_sha256":"23e05ca67b0f1db780953ca5094ffc1ba1aebb1aadbe19482f047cdf36f3e402"}}