{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SFU4RE4UGS6CRKLX2PWGRE3IYT","short_pith_number":"pith:SFU4RE4U","schema_version":"1.0","canonical_sha256":"9169c8939434bc28a977d3ec689368c4f5886c3aea8f50a74450dab6c7c41bdd","source":{"kind":"arxiv","id":"1707.01495","version":3},"attestation_state":"computed","paper":{"title":"Hindsight Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Ray, Bob McGrew, Filip Wolski, Jonas Schneider, Josh Tobin, Marcin Andrychowicz, Peter Welinder, Pieter Abbeel, Rachel Fong, Wojciech Zaremba","submitted_at":"2017-07-05T17:55:53Z","abstract_excerpt":"Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum.\n  We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in "},"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":"1707.01495","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T17:55:53Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO"],"title_canon_sha256":"e76dc2dfa302675a789b8b030df6dec51feb10089cc2de46985b7cd497f16951","abstract_canon_sha256":"4b471c36c86d238cf31184cc5feb90326f255f70017b163e6c5e0b85586c3a33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:44.659477Z","signature_b64":"XhOSHPyo+2ce375fTbSf9+f1z5c0Nxr6bUV1byM+RsQcLZRublzMepL9vDsZyie1sZoC/G80eBgXIMhqUEuKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9169c8939434bc28a977d3ec689368c4f5886c3aea8f50a74450dab6c7c41bdd","last_reissued_at":"2026-05-18T00:22:44.658995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:44.658995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hindsight Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Ray, Bob McGrew, Filip Wolski, Jonas Schneider, Josh Tobin, Marcin Andrychowicz, Peter Welinder, Pieter Abbeel, Rachel Fong, Wojciech Zaremba","submitted_at":"2017-07-05T17:55:53Z","abstract_excerpt":"Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum.\n  We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01495","kind":"arxiv","version":3},"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":"1707.01495","created_at":"2026-05-18T00:22:44.659077+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.01495v3","created_at":"2026-05-18T00:22:44.659077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01495","created_at":"2026-05-18T00:22:44.659077+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFU4RE4UGS6C","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFU4RE4UGS6CRKLX","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFU4RE4U","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2411.00361","citing_title":"Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18299","citing_title":"SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03599","citing_title":"Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11321","citing_title":"Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09364","citing_title":"Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17032","citing_title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT","json":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT.json","graph_json":"https://pith.science/api/pith-number/SFU4RE4UGS6CRKLX2PWGRE3IYT/graph.json","events_json":"https://pith.science/api/pith-number/SFU4RE4UGS6CRKLX2PWGRE3IYT/events.json","paper":"https://pith.science/paper/SFU4RE4U"},"agent_actions":{"view_html":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT","download_json":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT.json","view_paper":"https://pith.science/paper/SFU4RE4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.01495&json=true","fetch_graph":"https://pith.science/api/pith-number/SFU4RE4UGS6CRKLX2PWGRE3IYT/graph.json","fetch_events":"https://pith.science/api/pith-number/SFU4RE4UGS6CRKLX2PWGRE3IYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT/action/storage_attestation","attest_author":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT/action/author_attestation","sign_citation":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT/action/citation_signature","submit_replication":"https://pith.science/pith/SFU4RE4UGS6CRKLX2PWGRE3IYT/action/replication_record"}},"created_at":"2026-05-18T00:22:44.659077+00:00","updated_at":"2026-05-18T00:22:44.659077+00:00"}