{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4URK6WDAIVNOL2FP76FTDS5KWD","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":"6e440e842f10ccaf3cd60b00f07fb5e87319ae89470dfb01d6a340ba16c0e97e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T21:15:37Z","title_canon_sha256":"0d134e57c3cb5bf6323eeb758bb5ac4edc4b75546c96503486725bb3ffe3f925"},"schema_version":"1.0","source":{"id":"2506.17263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17263","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17263v1","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17263","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"4URK6WDAIVNO","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"4URK6WDAIVNOL2FP","created_at":"2026-07-05T11:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"4URK6WDA","created_at":"2026-07-05T11:25:14Z"}],"graph_snapshots":[{"event_id":"sha256:bc9cc66a7cc3845020f8ca97390ba7a1c844d8624686c3333f24e2157ee203ec","target":"graph","created_at":"2026-07-05T11:25:14Z","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/2506.17263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Resource constraints can fundamentally change both learning and decision-making. We explore how memory constraints influence an agent's performance when navigating unknown environments using standard reinforcement learning algorithms. Specifically, memory-constrained agents face a dilemma: how much of their limited memory should be allocated to each of the agent's internal processes, such as estimating a world model, as opposed to forming a plan using that model? We study this dilemma in MCTS- and DQN-based algorithms and examine how different allocations of memory impact performance in episod","authors_text":"David Abel, Massimiliano Tamborski","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T21:15:37Z","title":"Memory Allocation in Resource-Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17263","kind":"arxiv","version":1},"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:da3536d409dc724673609bfd71a5d0041bc7b9ac033792a9d596cbd5174f79b4","target":"record","created_at":"2026-07-05T11:25:14Z","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":"6e440e842f10ccaf3cd60b00f07fb5e87319ae89470dfb01d6a340ba16c0e97e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T21:15:37Z","title_canon_sha256":"0d134e57c3cb5bf6323eeb758bb5ac4edc4b75546c96503486725bb3ffe3f925"},"schema_version":"1.0","source":{"id":"2506.17263","kind":"arxiv","version":1}},"canonical_sha256":"e522af5860455ae5e8afff8b31cbaab0dcc686e08d7b910e201152d35dbbae3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e522af5860455ae5e8afff8b31cbaab0dcc686e08d7b910e201152d35dbbae3e","first_computed_at":"2026-07-05T11:25:14.446108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:14.446108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vACrbvoGoOwsqqvlyvHwBBkDkhSEu3ngBhX3MDXpKA1SOB5y640KGl+ZB90qdXUVhqH4xORno8NB5QnEKy0cCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:14.446535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da3536d409dc724673609bfd71a5d0041bc7b9ac033792a9d596cbd5174f79b4","sha256:bc9cc66a7cc3845020f8ca97390ba7a1c844d8624686c3333f24e2157ee203ec"],"state_sha256":"1b4174396048321923e348c0b07292b50915fcb92b01df71d542eef8a12c87a0"}