paper-with-me

Papers

Faster Reinforcement Learning by Freezing Slow States

2023-01-03 · Yijia Wang, Daniel R. Jiang

We study infinite horizon Markov decision processes (MDPs) with "fast-slow" structure, where some state variables evolve rapidly ("fast states") while others change more gradually ("slow states"). Such structure is common in real-world problems where sequential decisions need to be made at high frequencies over long horizons, where slowly evolving information also influences optimal decisions. Examples include inventory control under slowly changing demand, or dynamic pricing with gradually shifting consumer behavior. Modeling the problem at the natural decision frequency leads to MDPs with discount factors close to one, making them computationally challenging. We propose a novel approximation strategy that "freezes" slow states during a phase of lower-level planning, solving finite-horizon MDPs conditioned on a fixed slow state, and then applying value iteration to an auxiliary upper-level MDP that evolves on a slower timescale. Freezing states for short periods of time leads to easier-to-solve lower-level problems, while a slower upper-level timescale allows for a more favorable discount factor. On the theoretical side, we analyze the regret incurred by our frozen-state approach, which leads to simple insights on how to trade off computational budget versus regret. Empirically, we demonstrate that frozen-state methods produce high-quality policies with significantly less computation, and we show that simply omitting slow states is often a poor heuristic.

📄 PDF Abstract BibTeX arXiv:2301.00922

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Emergent Slow Thinking in LLMs as Inverse Tree Freezing

2025-09-28 · Sihan Hu, Xiansheng Cai, Yuan Huang, Zhiyuan Yao 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) enables large language models to acquire slow, multi-step reasoning from sparse final-answer signals. We provide a statistical-physics picture of this emergence. We s…

Reinforcement Learning

Enhanced Experience Replay Generation for Efficient Reinforcement Learning

2017-05-23 · Vincent Huang, Tobias Ley, Martha Vlachou-Konchylaki, Wenfeng Hu

Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The E…

Deep Reinforcement LearningGenerative Adversarial Networkreinforcement-learningReinforcement Learning+1

Ordered Network Analysis of Epistemic Emotions during Collaborative Problem Solving

2026-07-25 · Sifatul Anindho, Videep Venkatesha, Jaclyn Ocumpaugh, Nathaniel Blanchard arxiv

Investigating how affective states such as confusion and frustration persist and transition during co-situated collaborative problem solving (CPS) is important for understanding the dynamics of epistemic emotions. Howeve…

WSBD: Freezing-Based Optimizer for Quantum Neural Networks

2026-02-11 · Christopher Kverne, Mayur Akewar, Yuqian Huo, Tirthak Patel 외 arxiv

The training of Quantum Neural Networks (QNNs) is hindered by the high computational cost of gradient estimation and the barren plateau problem, where optimization landscapes become intractably flat. To address these cha…

Speeding up reinforcement learning by combining attention and agency features

2019-12-29 · Berkay Demirel, Martí Sánchez-Fibla

When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality. Reinforcement Learning (RL) has been able to deal with bi…

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)