{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598"},"schema_version":"1.0","source":{"id":"2409.05358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05358v2","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"VXCCAW7IRTJX","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"VXCCAW7IRTJXHRO4","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"VXCCAW7I","created_at":"2026-07-05T10:37:32Z"}],"graph_snapshots":[{"event_id":"sha256:b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8","target":"graph","created_at":"2026-07-05T10:37:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.05358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aly Lidayan, Michael Dennis, Stuart Russell","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05358","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae","target":"record","created_at":"2026-07-05T10:37:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598"},"schema_version":"1.0","source":{"id":"2409.05358","kind":"arxiv","version":2}},"canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","first_computed_at":"2026-07-05T10:37:32.652721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:32.652721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zp8VRbkM3Uc+TOgQ7kCphGz7UhrsQjdajzHmMLvH/2P0R7x8J9driFgTdR5DSK3dDXye0qA8Xqg3S3ovt1ZnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:32.653278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae","sha256:b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8"],"state_sha256":"1d83b83327919ed90f0865bd01af4f4912846bb813a351b8e2f96f7dd9c86c86"}