Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design

2025-03-07

AI Summary

This work systematically investigates the generalization capabilities of reinforcement learning (RL) in sequential experimental design. Addressing robustness bottlenecks under model misspecification and distributional shift, we propose a unified RL framework integrating dropout regularization and ensemble strategies across prominent algorithms—including PPO, SAC, and DQN. To our knowledge, this is the first systematic cross-task and parameter-perturbation generalization evaluation of diverse RL methods in this domain. Empirical results demonstrate that ensemble SAC and dropout-regularized PPO substantially enhance robustness: information gain improves by 18–32% over standard baselines under model mismatch and prior shift. Our core contribution lies in rigorously establishing the critical role of regularization and ensembling in improving generalization for RL-driven experimental design, while providing a reproducible, high-performance paradigm for constructing robust policy agents.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for experimental design problems, there is significantly less work on obtaining policies that are able to generalise well - i.e. able to give good performance despite a change in the underlying statistical properties of the experiments. Conducting experiments sequentially has recently brought about the use of reinforcement learning, where an agent is trained to navigate the design space to select the most informative designs for experimentation. However, there is still a lack of understanding about the benefits and drawbacks of using certain reinforcement learning algorithms to train these agents. In our work, we investigate several reinforcement learning algorithms and their efficacy in producing agents that take maximally informative design decisions in sequential experimental design scenarios. We find that agent performance is impacted depending on the algorithm used for training, and that particular algorithms, using dropout or ensemble approaches, empirically showcase attractive generalisation properties.

Problem

• Evaluate reinforcement learning algorithms for sequential experimental design.
• Assess generalization of policies across varying statistical properties.
• Compare effectiveness of dropout and ensemble methods in training.

Innovation

• Reinforcement learning for sequential experimental design
• Comparison of algorithms for informative design decisions
• Dropout and ensemble methods enhance generalization