{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:D4HKML3YDOIXN6XWKR75C7CAY4","short_pith_number":"pith:D4HKML3Y","schema_version":"1.0","canonical_sha256":"1f0ea62f781b9176faf6547fd17c40c730614d201aeef710824d98d42c4e9b10","source":{"kind":"arxiv","id":"1802.09464","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.09464","created_at":"2026-05-18T00:21:34.090260+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09464v2","created_at":"2026-05-18T00:21:34.090260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09464","created_at":"2026-05-18T00:21:34.090260+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4HKML3YDOIX","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4HKML3YDOIXN6XW","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4HKML3Y","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1906.09223","citing_title":"Disentangled Skill Embeddings for Reinforcement Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03508","citing_title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2102.04307","citing_title":"Learning Optimal Strategies for Temporal Tasks in Stochastic Games","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2410.06347","citing_title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21039","citing_title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11975","citing_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2510.09096","citing_title":"When a Robot is More Capable than a Human: Learning from Constrained Demonstrators","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13401","citing_title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11975","citing_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09157","citing_title":"Revisiting Mixture Policies in Entropy-Regularized Actor-Critic","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02461","citing_title":"Middle-mile logistics through the lens of goal-conditioned reinforcement learning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4","json":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4.json","graph_json":"https://pith.science/api/pith-number/D4HKML3YDOIXN6XWKR75C7CAY4/graph.json","events_json":"https://pith.science/api/pith-number/D4HKML3YDOIXN6XWKR75C7CAY4/events.json","paper":"https://pith.science/paper/D4HKML3Y"},"agent_actions":{"view_html":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4","download_json":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4.json","view_paper":"https://pith.science/paper/D4HKML3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09464&json=true","fetch_graph":"https://pith.science/api/pith-number/D4HKML3YDOIXN6XWKR75C7CAY4/graph.json","fetch_events":"https://pith.science/api/pith-number/D4HKML3YDOIXN6XWKR75C7CAY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/action/storage_attestation","attest_author":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/action/author_attestation","sign_citation":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/action/citation_signature","submit_replication":"https://pith.science/pith/D4HKML3YDOIXN6XWKR75C7CAY4/action/replication_record"}},"created_at":"2026-05-18T00:21:34.090260+00:00","updated_at":"2026-05-18T00:21:34.090260+00:00"}