paper-with-me

Papers

Optimizing Interpretable Decision Tree Policies for Reinforcement Learning

2024-08-21 · Daniël Vos, Sicco Verwer

Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained increased attention in supervised learning for their inherent interpretability, enabling modelers to understand the exact prediction process after learning. This paper considers the problem of optimizing interpretable decision tree policies to replace neural networks in reinforcement learning settings. Previous works have relaxed the tree structure, restricted to optimizing only tree leaves, or applied imitation learning techniques to approximately copy the behavior of a neural network policy with a decision tree. We propose the Decision Tree Policy Optimization (DTPO) algorithm that directly optimizes the complete decision tree using policy gradients. Our technique uses established decision tree heuristics for regression to perform policy optimization. We empirically show that DTPO is a competitive algorithm compared to imitation learning algorithms for optimizing decision tree policies in reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2408.11632

Code (1)

tudelft-cda-lab/dtpo 공식 구현 jax

Tasks

Imitation Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy

2019-07-02 · Aaron M. Roth, Nicholay Topin, Pooyan Jamshidi, Manuela Veloso

There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpretability of reinforcement learning by in…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes

2025-10-22 · Xuyuan Xiong, Pedro Chumpitaz-Flores, Kaixun Hua, Cheng Hua arxiv

Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method …

Reinforcement Learning

MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning

2022-05-25 · Stephanie Milani, Zhicheng Zhang, Nicholay Topin, Zheyuan Ryan Shi 외

Many recent breakthroughs in multi-agent reinforcement learning (MARL) require the use of deep neural networks, which are challenging for human experts to interpret and understand. On the other hand, existing work on int…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods

2021-02-25 · Nicholay Topin, Stephanie Milani, Fei Fang, Manuela Veloso

Current work in explainable reinforcement learning generally produces policies in the form of a decision tree over the state space. Such policies can be used for formal safety verification, agent behavior prediction, and…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning

2024-05-23 · Hector Kohler, Quentin Delfosse, Riad Akrour, Kristian Kersting 외

Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So…

Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning