paper-with-me

홈 › Papers

On overfitting and asymptotic bias in batch reinforcement learning with partial observability

2017-09-22 · Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau

This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability. Our theoretical analysis formally characterizes that while potentially increasing the asymptotic bias, a smaller state representation decreases the risk of overfitting. This analysis relies on expressing the quality of a state representation by bounding L1 error terms of the associated belief states. Theoretical results are empirically illustrated when the state representation is a truncated history of observations, both on synthetic POMDPs and on a large-scale POMDP in the context of smartgrids, with real-world data. Finally, similarly to known results in the fully observable setting, we also briefly discuss and empirically illustrate how using function approximators and adapting the discount factor may enhance the tradeoff between asymptotic bias and overfitting in the partially observable context.

📄 PDF Abstract BibTeX arXiv:1709.07796

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Stability and Generalisation in Batch Reinforcement Learning

2021-09-29 · Matthew J. A. Smith, Shimon Whiteson

Overfitting has been recently acknowledged as a key limiting factor in the capabilities of reinforcement learning algorithms, despite little theoretical characterisation. We provide a theoretical examination of overfitti…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Non-asymptotic bounds for stochastic optimization with biased noisy gradient oracles

2020-02-26 · Nirav Bhavsar, Prashanth L. A

We introduce biased gradient oracles to capture a setting where the function measurements have an estimation error that can be controlled through a batch size parameter. Our proposed oracles are appealing in several prac…

Stochastic Optimization

Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias

2024-06-13 · Honam Wong, Wendao Wu, Fanghui Liu, Yiping Lu

Recent advances in machine learning have inspired a surge of research into reconstructing specific quantities of interest from measurements that comply with certain physical laws. These efforts focus on inverse problems …

Inductive Biasregression

Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters

2024-08-18 · Abhinandan Dalal, Patrick Blöbaum, Shiva Kasiviswanathan, Aaditya Ramdas

Double (debiased) machine learning (DML) has seen widespread use in recent years for learning causal/structural parameters, in part due to its flexibility and adaptability to high-dimensional nuisance functions as well a…

valid

Benchmarking Batch Deep Reinforcement Learning Algorithms

2019-10-03 · Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh, Joelle Pineau

Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several pap…

BenchmarkingDeep Reinforcement LearningQ-Learningreinforcement-learning+2