{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","short_pith_number":"pith:VXCCAW7I","schema_version":"1.0","canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","source":{"kind":"arxiv","id":"2409.05358","version":2},"attestation_state":"computed","paper":{"title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aly Lidayan, Michael Dennis, Stuart Russell","submitted_at":"2024-09-09T06:39:56Z","abstract_excerpt":"Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encourage counterproductive exploits, e.g., fixation with noisy TV screens. Here we provide a theoretical model which anticipates these behaviors, and provides broad criteria under which adverse effects can be bounded. We characterize all pseudo-rewards as reward shaping in Bayes-Adaptive Markov Decision Processes (BAMDPs), which formulates the problem of learning in MDPs as an MDP over the agent's knowledge. Optimal expl"},"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":"2409.05358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598","abstract_canon_sha256":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:32.653278Z","signature_b64":"Zp8VRbkM3Uc+TOgQ7kCphGz7UhrsQjdajzHmMLvH/2P0R7x8J9driFgTdR5DSK3dDXye0qA8Xqg3S3ovt1ZnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","last_reissued_at":"2026-07-05T10:37:32.652721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:32.652721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aly Lidayan, Michael Dennis, Stuart Russell","submitted_at":"2024-09-09T06:39:56Z","abstract_excerpt":"Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encourage counterproductive exploits, e.g., fixation with noisy TV screens. Here we provide a theoretical model which anticipates these behaviors, and provides broad criteria under which adverse effects can be bounded. We characterize all pseudo-rewards as reward shaping in Bayes-Adaptive Markov Decision Processes (BAMDPs), which formulates the problem of learning in MDPs as an MDP over the agent's knowledge. Optimal expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05358","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/2409.05358/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":"2409.05358","created_at":"2026-07-05T10:37:32.652781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05358v2","created_at":"2026-07-05T10:37:32.652781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05358","created_at":"2026-07-05T10:37:32.652781+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXCCAW7IRTJX","created_at":"2026-07-05T10:37:32.652781+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXCCAW7IRTJXHRO4","created_at":"2026-07-05T10:37:32.652781+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXCCAW7I","created_at":"2026-07-05T10:37:32.652781+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/VXCCAW7IRTJXHRO4XJBL27KOEG","json":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG.json","graph_json":"https://pith.science/api/pith-number/VXCCAW7IRTJXHRO4XJBL27KOEG/graph.json","events_json":"https://pith.science/api/pith-number/VXCCAW7IRTJXHRO4XJBL27KOEG/events.json","paper":"https://pith.science/paper/VXCCAW7I"},"agent_actions":{"view_html":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG","download_json":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG.json","view_paper":"https://pith.science/paper/VXCCAW7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05358&json=true","fetch_graph":"https://pith.science/api/pith-number/VXCCAW7IRTJXHRO4XJBL27KOEG/graph.json","fetch_events":"https://pith.science/api/pith-number/VXCCAW7IRTJXHRO4XJBL27KOEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/action/storage_attestation","attest_author":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/action/author_attestation","sign_citation":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/action/citation_signature","submit_replication":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/action/replication_record"}},"created_at":"2026-07-05T10:37:32.652781+00:00","updated_at":"2026-07-05T10:37:32.652781+00:00"}