{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4FKT4AYDJHUM65XJ25BNX5IC7A","short_pith_number":"pith:4FKT4AYD","schema_version":"1.0","canonical_sha256":"e1553e030349e8cf76e9d742dbf502f83bd693476122522384356d9eafea84f2","source":{"kind":"arxiv","id":"1907.01657","version":2},"attestation_state":"computed","paper":{"title":"Dynamics-Aware Unsupervised Discovery of Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Archit Sharma, Karol Hausman, Sergey Levine, Shixiang Gu, Vikash Kumar","submitted_at":"2019-07-02T21:32:19Z","abstract_excerpt":"Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors and solve diverse tasks. However, learning an accurate model for complex dynamical systems is difficult, and even then, the model might not generalize well outside the distribution of states on which it was trained. In this work, we combine model-based learning with model-free learning of primitives that make model-based planning easy. To that end, we aim to answer the questio"},"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":"1907.01657","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-02T21:32:19Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"21d29e25b2109fb9b8ce3c926c2bfcf31ae6ef1a23ae60b03d21e07f38a13188","abstract_canon_sha256":"dd6c5854cba041b605cad4c13a65f3e39ecd163146d7e98136d15c2173a0e718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:56.597084Z","signature_b64":"f7iSdP5Vef747MV2nDKrDPRX/JBi1cF6tq61pfZ62enzZqXhLRjni3USMUW91jdvfFgPCmnij1Se2z5ekjjpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1553e030349e8cf76e9d742dbf502f83bd693476122522384356d9eafea84f2","last_reissued_at":"2026-07-05T00:40:56.596638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:56.596638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamics-Aware Unsupervised Discovery of Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Archit Sharma, Karol Hausman, Sergey Levine, Shixiang Gu, Vikash Kumar","submitted_at":"2019-07-02T21:32:19Z","abstract_excerpt":"Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors and solve diverse tasks. However, learning an accurate model for complex dynamical systems is difficult, and even then, the model might not generalize well outside the distribution of states on which it was trained. In this work, we combine model-based learning with model-free learning of primitives that make model-based planning easy. To that end, we aim to answer the questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01657","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1907.01657/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":"1907.01657","created_at":"2026-07-05T00:40:56.596695+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01657v2","created_at":"2026-07-05T00:40:56.596695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01657","created_at":"2026-07-05T00:40:56.596695+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FKT4AYDJHUM","created_at":"2026-07-05T00:40:56.596695+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FKT4AYDJHUM65XJ","created_at":"2026-07-05T00:40:56.596695+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FKT4AYD","created_at":"2026-07-05T00:40:56.596695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19998","citing_title":"Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09476","citing_title":"Goal Sets, Not Goal States: Queryable Robot Goals through Goal-Set Hindsight Relabeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08735","citing_title":"Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29201","citing_title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12261","citing_title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24558","citing_title":"Hierarchical Behaviour Spaces","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06145","citing_title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","ref_index":23,"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":165,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A","json":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A.json","graph_json":"https://pith.science/api/pith-number/4FKT4AYDJHUM65XJ25BNX5IC7A/graph.json","events_json":"https://pith.science/api/pith-number/4FKT4AYDJHUM65XJ25BNX5IC7A/events.json","paper":"https://pith.science/paper/4FKT4AYD"},"agent_actions":{"view_html":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A","download_json":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A.json","view_paper":"https://pith.science/paper/4FKT4AYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01657&json=true","fetch_graph":"https://pith.science/api/pith-number/4FKT4AYDJHUM65XJ25BNX5IC7A/graph.json","fetch_events":"https://pith.science/api/pith-number/4FKT4AYDJHUM65XJ25BNX5IC7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A/action/storage_attestation","attest_author":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A/action/author_attestation","sign_citation":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A/action/citation_signature","submit_replication":"https://pith.science/pith/4FKT4AYDJHUM65XJ25BNX5IC7A/action/replication_record"}},"created_at":"2026-07-05T00:40:56.596695+00:00","updated_at":"2026-07-05T00:40:56.596695+00:00"}