paper-with-me

홈 › Papers

Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs

2024-04-22 · Lili Wu, Ben Evans, Riashat Islam, Raihan Seraj, Yonathan Efroni, Alex Lamb

Discovering an informative, or agent-centric, state representation that encodes only the relevant information while discarding the irrelevant is a key challenge towards scaling reinforcement learning algorithms and efficiently applying them to downstream tasks. Prior works studied this problem in high-dimensional Markovian environments, when the current observation may be a complex object but is sufficient to decode the informative state. In this work, we consider the problem of discovering the agent-centric state in the more challenging high-dimensional non-Markovian setting, when the state can be decoded from a sequence of past observations. We establish that generalized inverse models can be adapted for learning agent-centric state representation for this task. Our results include asymptotic theory in the deterministic dynamics setting as well as counter-examples for alternative intuitive algorithms. We complement these findings with a thorough empirical study on the agent-centric state discovery abilities of the different alternatives we put forward. Particularly notable is our analysis of past actions, where we show that these can be a double-edged sword: making the algorithms more successful when used correctly and causing dramatic failure when used incorrectly.

📄 PDF Abstract BibTeX arXiv:2404.14552

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata

2021-03-10 · Tianyu Wang, Nikolay Atanasov

This paper presents a method for learning logical task specifications and cost functions from demonstrations. Constructing specifications by hand is challenging for complex objectives and constraints in autonomous system…

reinforcement-learningReinforcement Learning (RL)

Inverse Decision Modeling: Learning Interpretable Representations of Behavior

2023-10-28 · Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we dev…

Descriptive

Identifiability in inverse reinforcement learning

2021-06-07 · NeurIPS 2021 12 · Haoyang Cao, Samuel N. Cohen, Lukasz Szpruch

Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions. As already observed in Russell [1998] the problem is ill-posed, and the reward…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

On $L_2$-consistency of nearest neighbor matching

2019-02-06 · James Sharpnack

Biased sampling and missing data complicates statistical problems ranging from causal inference to reinforcement learning. We often correct for biased sampling of summary statistics with matching methods and importance w…

Causal InferenceDomain AdaptationImputationreinforcement-learning+1

The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks

2024-08-15 · Philipp Holl, Nils Thuerey

Finding model parameters from data is an essential task in science and engineering, from weather and climate forecasts to plasma control. Previous works have employed neural networks to greatly accelerate finding solutio…