{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3LN57UI4JCZ54NB4KM65LVIV7","short_pith_number":"pith:D3LN57UI","schema_version":"1.0","canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","source":{"kind":"arxiv","id":"2402.07019","version":1},"attestation_state":"computed","paper":{"title":"Informativeness of Reward Functions in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze","submitted_at":"2024-02-10T18:36:42Z","abstract_excerpt":"Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards speed up the agent's convergence. In particular, we consider expert-driven reward design settings where an expert or teacher seeks to provide informative and interpretable rewards to a learning agent. Existing works have considered several different reward design formulations; however, the key challenge is formulating a reward informativeness criterion that ad"},"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":"2402.07019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"9ae1e4cc4f7b81c69e43df85ce9ee5b962ce7b67f2afa6d3dab1ee621b94424c","abstract_canon_sha256":"d1122443e9f8743d50cc49b542903c5189e180dcd3dd362aa7d87fa6632ba59d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:42.594421Z","signature_b64":"Qz12ulCzfeIrGGOPQq8bwqvnokwzN0KMgDEBE14YfViFOAvuUfzBeP53Nj2hyAUbbnjkZeI89zREX2cbuMYlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","last_reissued_at":"2026-07-05T07:43:42.594021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:42.594021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Informativeness of Reward Functions in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze","submitted_at":"2024-02-10T18:36:42Z","abstract_excerpt":"Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards speed up the agent's convergence. In particular, we consider expert-driven reward design settings where an expert or teacher seeks to provide informative and interpretable rewards to a learning agent. Existing works have considered several different reward design formulations; however, the key challenge is formulating a reward informativeness criterion that ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07019","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/2402.07019/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":"2402.07019","created_at":"2026-07-05T07:43:42.594082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07019v1","created_at":"2026-07-05T07:43:42.594082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07019","created_at":"2026-07-05T07:43:42.594082+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3LN57UI4JCZ","created_at":"2026-07-05T07:43:42.594082+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3LN57UI4JCZ54NB","created_at":"2026-07-05T07:43:42.594082+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3LN57UI","created_at":"2026-07-05T07:43:42.594082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19773","citing_title":"PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7","json":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7.json","graph_json":"https://pith.science/api/pith-number/D3LN57UI4JCZ54NB4KM65LVIV7/graph.json","events_json":"https://pith.science/api/pith-number/D3LN57UI4JCZ54NB4KM65LVIV7/events.json","paper":"https://pith.science/paper/D3LN57UI"},"agent_actions":{"view_html":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7","download_json":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7.json","view_paper":"https://pith.science/paper/D3LN57UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07019&json=true","fetch_graph":"https://pith.science/api/pith-number/D3LN57UI4JCZ54NB4KM65LVIV7/graph.json","fetch_events":"https://pith.science/api/pith-number/D3LN57UI4JCZ54NB4KM65LVIV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/action/storage_attestation","attest_author":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/action/author_attestation","sign_citation":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/action/citation_signature","submit_replication":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/action/replication_record"}},"created_at":"2026-07-05T07:43:42.594082+00:00","updated_at":"2026-07-05T07:43:42.594082+00:00"}