Pith. sign in

REVIEW 5 cited by

Continual Learning as Computationally Constrained Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.04345 v3 pith:UFZL2HBV submitted 2023-07-10 cs.LG cs.AI

Saurabh Kumar , Henrik Marklund , Ashish Rao , Yifan Zhu , Hong Jun Jeon , Yueyang Liu , Benjamin Van Roy This is my paper · ORCID
classification cs.LGcs.AI
keywords learningcontinualartificialintelligenceaccumulatesaddressedadvanceagent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills over a long lifetime could advance the frontier of artificial intelligence capabilities. The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning. This monograph clarifies and formalizes concepts of continual learning, introducing a framework and set of tools to stimulate further research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Decision Making in Hybrid Environments: A Model Aggregation Approach

    cs.LG 2025-02 conditional novelty 7.0 of 10

    An aggregation-based extension of the DEC complexity measure yields new regret bounds for hybrid stochastic-adversarial RL and the first square-root-T regret for linear Q-star/V-star MDPs.

  2. Capacity-Constrained Continual Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    An LQG predictor constrained to keep at most B bits of information about its observation history is optimally solved by a rate-distortion compressed Kalman estimate, with water-filling capacity allocation across subsystems.

  3. Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Reducing churn in continual RL via C-CHAIN prevents NTK rank collapse and substantially improves learning across four benchmark suites.

  4. Optimizers Qualitatively Alter Solutions And We Should Leverage This

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Deep learning optimizers should be designed to induce desired solution properties, not just convergence speed; different optimizers demonstrably land in qualitatively different minima.

  5. Memory Allocation in Resource-Constrained Reinforcement Learning

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Memory allocation between model and plan affects performance in memory-constrained RL, with a balanced split often optimal.

Pith tools