mlsanityData to 14 Oct 2026

Memory Allocation in Resource-Constrained Reinforcement Learning

arXiv 2506.17263 ↗First posted 9 Jun 2025cs.LG cs.AIcited by 2

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

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 episodic and continual learning settings.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 23 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

11 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Satisficing Exploration for Deep Reinforcement Learning16 Jul

Other references · 10

  1. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  2. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  3. 2023A Definition of Continual Reinforcement Learningcited by 101
  4. 2021People construct simplified mental representations to plancited by 47
  5. 2021Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent Statescited by 43
  6. 2023Continual Learning as Computationally Constrained Reinforcement Learningcited by 37
  7. 2020Selective Dyna-style Planning Under Limited Model Capacitycited by 30
  8. 2020Jelly Bean World: A Testbed for Never-Ending Learningcited by 19
  9. 2023Prediction and Control in Continual Reinforcement Learningcited by 19
  10. 2024The Need for a Big World Simulator: A Scientific Challenge for Continual Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Position: Deployed Reinforcement Learning should be Continualcited by 1
  2. 2026Artifacts as Memory Beyond the Agent Boundarycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
  2. 2026Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
  3. 2024Reinforcement Learning for Dynamic Memory Allocation
  4. 2025Memento 2: Learning by Stateful Reflective Memory
  5. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  6. 2025Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management
  7. 2026MemoWM: How World Models Change What Agents Need to Remember
  8. 2026Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning