{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q7RL45ZPOCJ6OLICMXIQN6VMOI","short_pith_number":"pith:Q7RL45ZP","schema_version":"1.0","canonical_sha256":"87e2be772f7093e72d0265d106faac72111e6b7978c90316417ae05c5f3114a8","source":{"kind":"arxiv","id":"2111.04120","version":1},"attestation_state":"computed","paper":{"title":"Automatic Goal Generation using Dynamical Distance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin","submitted_at":"2021-11-07T16:23:56Z","abstract_excerpt":"Reinforcement Learning (RL) agents can learn to solve complex sequential decision making tasks by interacting with the environment. However, sample efficiency remains a major challenge. In the field of multi-goal RL, where agents are required to reach multiple goals to solve complex tasks, improving sample efficiency can be especially challenging. On the other hand, humans or other biological agents learn such tasks in a much more strategic way, following a curriculum where tasks are sampled with increasing difficulty level in order to make gradual and efficient learning progress. In this work"},"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":"2111.04120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T16:23:56Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b0fee7c653cdc7a93caeb003b14c1040ae2ba1212b601026a96f6253b4588ca5","abstract_canon_sha256":"87644d2e46a394600bea88069ab164110b71f67ad3ff6eeebb555f74d19095ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:55.974346Z","signature_b64":"tdlafFZvwA3jiAf7E7/zJzjCMsPcSreEdRVw+b29B22GvAVExWv2C4Z77Ab7b+vWEA36DOzNV6WguB7RVHJXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87e2be772f7093e72d0265d106faac72111e6b7978c90316417ae05c5f3114a8","last_reissued_at":"2026-07-05T03:29:55.973760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:55.973760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Goal Generation using Dynamical Distance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin","submitted_at":"2021-11-07T16:23:56Z","abstract_excerpt":"Reinforcement Learning (RL) agents can learn to solve complex sequential decision making tasks by interacting with the environment. However, sample efficiency remains a major challenge. In the field of multi-goal RL, where agents are required to reach multiple goals to solve complex tasks, improving sample efficiency can be especially challenging. On the other hand, humans or other biological agents learn such tasks in a much more strategic way, following a curriculum where tasks are sampled with increasing difficulty level in order to make gradual and efficient learning progress. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04120","kind":"arxiv","version":1},"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/2111.04120/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.04120","created_at":"2026-07-05T03:29:55.973901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.04120v1","created_at":"2026-07-05T03:29:55.973901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04120","created_at":"2026-07-05T03:29:55.973901+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7RL45ZPOCJ6","created_at":"2026-07-05T03:29:55.973901+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7RL45ZPOCJ6OLIC","created_at":"2026-07-05T03:29:55.973901+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7RL45ZP","created_at":"2026-07-05T03:29:55.973901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI","json":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI.json","graph_json":"https://pith.science/api/pith-number/Q7RL45ZPOCJ6OLICMXIQN6VMOI/graph.json","events_json":"https://pith.science/api/pith-number/Q7RL45ZPOCJ6OLICMXIQN6VMOI/events.json","paper":"https://pith.science/paper/Q7RL45ZP"},"agent_actions":{"view_html":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI","download_json":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI.json","view_paper":"https://pith.science/paper/Q7RL45ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.04120&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7RL45ZPOCJ6OLICMXIQN6VMOI/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7RL45ZPOCJ6OLICMXIQN6VMOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI/action/storage_attestation","attest_author":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI/action/author_attestation","sign_citation":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI/action/citation_signature","submit_replication":"https://pith.science/pith/Q7RL45ZPOCJ6OLICMXIQN6VMOI/action/replication_record"}},"created_at":"2026-07-05T03:29:55.973901+00:00","updated_at":"2026-07-05T03:29:55.973901+00:00"}