Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol

• URL: http://arxiv.org/abs/2502.08021v1
• Date: Tue, 11 Feb 2025 23:40:55 GMT
• Title: Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
• Authors: Pai Liu, Lingfeng Zhao, Shivangi Agarwal, Jinghan Liu, Audrey Huang, Philip Amortila, Nan Jiang,
• Abstract summary: We develop a new protocol for evaluating model-free and model-based selectors. We find that our new model-free selector, LSTD-Tournament, demonstrates promising empirical performance.
• Score: 12.46794226683161
• License:
• Abstract: Holdout validation and hyperparameter tuning from data is a long-standing problem in offline reinforcement learning (RL). A standard framework is to use off-policy evaluation (OPE) methods to evaluate and select the policies, but OPE either incurs exponential variance (e.g., importance sampling) or has hyperparameters on their own (e.g., FQE and model-based). In this work we focus on hyperparameter tuning for OPE itself, which is even more under-investigated. Concretely, we select among candidate value functions ("model-free") or dynamics ("model-based") to best assess the performance of a target policy. Our contributions are two fold. We develop: (1) new model-free and model-based selectors with theoretical guarantees, and (2) a new experimental protocol for empirically evaluating them. Compared to the model-free protocol in prior works, our new protocol allows for more stable generation of candidate value functions, better control of misspecification, and evaluation of model-free and model-based methods alike. We exemplify the protocol on a Gym environment, and find that our new model-free selector, LSTD-Tournament, demonstrates promising empirical performance.

Related papers

• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective. The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning. The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Realistic Evaluation of Test-Time Adaptation Algorithms: Unsupervised Hyperparameter Selection [1.4530711901349282]
  Test-Time Adaptation (TTA) has emerged as a promising strategy for tackling the problem of machine learning model robustness under distribution shifts. We evaluate existing TTA methods using surrogate-based hp-selection strategies to obtain a more realistic evaluation of their performance.
  arXiv  Detail & Related papers  (2024-07-19T11:58:30Z)
• Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning [32.24146877835396]
  We propose emphPlan To Predict (P2P), a framework that treats the model rollout process as a sequential decision making problem. We show that P2P achieves state-of-the-art performance on several challenging benchmark tasks.
  arXiv  Detail & Related papers  (2023-01-20T10:17:22Z)
• Out-of-sample scoring and automatic selection of causal estimators [0.0]
  We propose novel scoring approaches for both the CATE case and an important subset of instrumental variable problems. We implement that in an open source package that relies on DoWhy and EconML libraries.
  arXiv  Detail & Related papers  (2022-12-20T08:29:18Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Error-based Knockoffs Inference for Controlled Feature Selection [49.99321384855201]
  We propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees.
  arXiv  Detail & Related papers  (2022-03-09T01:55:59Z)
• Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic [67.00475077281212]
  Model-based reinforcement learning algorithms are more sample efficient than their model-free counterparts. We propose a novel approach that achieves high sample efficiency without the strong reliance on accurate learned models. We show that CMBAC significantly outperforms state-of-the-art approaches in terms of sample efficiency on several challenging tasks.
  arXiv  Detail & Related papers  (2021-12-16T15:33:11Z)
• Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings [13.376364233897528]
  Reinforcement learning can be used to learn treatment policies and aid decision making in healthcare. A standard validation pipeline for model selection requires running a learned policy in the actual environment. Our work serves as a practical guide for offline RL model selection and can help RL practitioners select policies using real-world datasets.
  arXiv  Detail & Related papers  (2021-07-23T02:41:51Z)
• COMBO: Conservative Offline Model-Based Policy Optimization [120.55713363569845]
  Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We develop a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-actions. We find that COMBO consistently performs as well or better as compared to prior offline model-free and model-based methods.
  arXiv  Detail & Related papers  (2021-02-16T18:50:32Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.