{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4URK6WDAIVNOL2FP76FTDS5KWD","short_pith_number":"pith:4URK6WDA","schema_version":"1.0","canonical_sha256":"e522af5860455ae5e8afff8b31cbaab0dcc686e08d7b910e201152d35dbbae3e","source":{"kind":"arxiv","id":"2506.17263","version":1},"attestation_state":"computed","paper":{"title":"Memory Allocation in Resource-Constrained Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Abel, Massimiliano Tamborski","submitted_at":"2025-06-09T21:15:37Z","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"},"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":"2506.17263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T21:15:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d134e57c3cb5bf6323eeb758bb5ac4edc4b75546c96503486725bb3ffe3f925","abstract_canon_sha256":"6e440e842f10ccaf3cd60b00f07fb5e87319ae89470dfb01d6a340ba16c0e97e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:14.446535Z","signature_b64":"vACrbvoGoOwsqqvlyvHwBBkDkhSEu3ngBhX3MDXpKA1SOB5y640KGl+ZB90qdXUVhqH4xORno8NB5QnEKy0cCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e522af5860455ae5e8afff8b31cbaab0dcc686e08d7b910e201152d35dbbae3e","last_reissued_at":"2026-07-05T11:25:14.446108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:14.446108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Allocation in Resource-Constrained Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Abel, Massimiliano Tamborski","submitted_at":"2025-06-09T21:15:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17263","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/2506.17263/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":"2506.17263","created_at":"2026-07-05T11:25:14.446162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17263v1","created_at":"2026-07-05T11:25:14.446162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17263","created_at":"2026-07-05T11:25:14.446162+00:00"},{"alias_kind":"pith_short_12","alias_value":"4URK6WDAIVNO","created_at":"2026-07-05T11:25:14.446162+00:00"},{"alias_kind":"pith_short_16","alias_value":"4URK6WDAIVNOL2FP","created_at":"2026-07-05T11:25:14.446162+00:00"},{"alias_kind":"pith_short_8","alias_value":"4URK6WDA","created_at":"2026-07-05T11:25:14.446162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08756","citing_title":"Artifacts as Memory Beyond the Agent Boundary","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD","json":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD.json","graph_json":"https://pith.science/api/pith-number/4URK6WDAIVNOL2FP76FTDS5KWD/graph.json","events_json":"https://pith.science/api/pith-number/4URK6WDAIVNOL2FP76FTDS5KWD/events.json","paper":"https://pith.science/paper/4URK6WDA"},"agent_actions":{"view_html":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD","download_json":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD.json","view_paper":"https://pith.science/paper/4URK6WDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17263&json=true","fetch_graph":"https://pith.science/api/pith-number/4URK6WDAIVNOL2FP76FTDS5KWD/graph.json","fetch_events":"https://pith.science/api/pith-number/4URK6WDAIVNOL2FP76FTDS5KWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD/action/storage_attestation","attest_author":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD/action/author_attestation","sign_citation":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD/action/citation_signature","submit_replication":"https://pith.science/pith/4URK6WDAIVNOL2FP76FTDS5KWD/action/replication_record"}},"created_at":"2026-07-05T11:25:14.446162+00:00","updated_at":"2026-07-05T11:25:14.446162+00:00"}