Active observing in continuous-time control
The control of continuous-time environments while actively deciding when to take costly
observations in time is a crucial yet unexplored problem, particularly relevant to real-world …
observations in time is a crucial yet unexplored problem, particularly relevant to real-world …
Learning long-term crop management strategies with cyclesgym
To improve the sustainability and resilience of modern food systems, designing improved
crop management strategies is crucial. The increasing abundance of data on agricultural …
crop management strategies is crucial. The increasing abundance of data on agricultural …
Reinforcement learning with state observation costs in action-contingent noiselessly observable markov decision processes
HJA Nam, S Fleming… - Advances in Neural …, 2021 - proceedings.neurips.cc
Many real-world problems that require making optimal sequences of decisions under
uncertainty involve costs when the agent wishes to obtain information about its environment …
uncertainty involve costs when the agent wishes to obtain information about its environment …
Automated scientific discovery: from equation discovery to autonomous discovery systems
The paper surveys automated scientific discovery, from equation discovery and symbolic
regression to autonomous discovery systems and agents. It discusses the individual …
regression to autonomous discovery systems and agents. It discusses the individual …
Act-then-measure: reinforcement learning for partially observable environments with active measuring
We study Markov decision processes (MDPs), where agents control when and how they
gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO …
gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO …
Dynamic observation policies in observation cost-sensitive reinforcement learning
Reinforcement learning (RL) has been shown to learn sophisticated control policies for
complex tasks including games, robotics, heating and cooling systems and text generation …
complex tasks including games, robotics, heating and cooling systems and text generation …
Mean-field games of speedy information access with observation costs
We investigate a mean-field game (MFG) in which agents can exercise control actions that
affect their speed of access to information. The agents can dynamically decide to receive …
affect their speed of access to information. The agents can dynamically decide to receive …
Remote Estimation of Markov Processes over Costly Channels: On the Benefits of Implicit Information
In this paper, we study the remote estimation problem of a Markov process over a channel
with a cost. We formulate this problem as an infinite horizon optimization problem with two …
with a cost. We formulate this problem as an infinite horizon optimization problem with two …
Monitored Markov Decision Processes
In reinforcement learning (RL), an agent learns to perform a task by interacting with an
environment and receiving feedback (a numerical reward) for its actions. However, the …
environment and receiving feedback (a numerical reward) for its actions. However, the …
Time and temporal abstraction in continual learning: tradeoffs, analogies and regret in an active measuring setting
V Létourneau, C Bellinger… - … on Lifelong Learning …, 2023 - proceedings.mlr.press
This conceptual paper provides theoretical results linking notions in semi-supervised
learning (SSL) and hierarchical reinforcement learning (HRL) in the context of lifelong …
learning (SSL) and hierarchical reinforcement learning (HRL) in the context of lifelong …