Evolutionary learning of interpretable decision trees

12/14/2020
by   Leonardo Lucio Custode, et al.
12

Reinforcement learning techniques achieved human-level performance in several tasks in the last decade. However, in recent years, the need for interpretability emerged: we want to be able to understand how a system works and the reasons behind its decisions. Not only we need interpretability to assess the safety of the produced systems, we also need it to extract knowledge about unknown problems. While some techniques that optimize decision trees for reinforcement learning do exist, they usually employ greedy algorithms or they do not exploit the rewards given by the environment. This means that these techniques may easily get stuck in local optima. In this work, we propose a novel approach to interpretable reinforcement learning that uses decision trees. We present a two-level optimization scheme that combines the advantages of evolutionary algorithms with the advantages of Q-learning. This way we decompose the problem into two sub-problems: the problem of finding a meaningful and useful decomposition of the state space, and the problem of associating an action to each state. We test the proposed method on three well-known reinforcement learning benchmarks, on which it results competitive with respect to the state-of-the-art in both performance and interpretability. Finally, we perform an ablation study that confirms that using the two-level optimization scheme gives a boost in performance in non-trivial environments with respect to a one-layer optimization technique.

READ FULL TEXT
research
08/17/2022

Quality Diversity Evolutionary Learning of Decision Trees

Addressing the need for explainable Machine Learning has emerged as one ...
research
03/22/2019

Interpretable Reinforcement Learning via Differentiable Decision Trees

Decision trees are ubiquitous in machine learning for their ease of use ...
research
09/19/2018

Interpretable Reinforcement Learning with Ensemble Methods

We propose to use boosted regression trees as a way to compute human-int...
research
02/03/2020

Evolutionary algorithms for constructing an ensemble of decision trees

Most decision tree induction algorithms are based on a greedy top-down r...
research
09/15/2022

MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees

Multi-agent reinforcement learning (MARL) recently has achieved tremendo...
research
05/16/2022

Many Field Packet Classification with Decomposition and Reinforcement Learning

Scalable packet classification is a key requirement to support scalable ...
research
05/05/2023

Learning Decision Trees with Gradient Descent

Decision Trees (DTs) are commonly used for many machine learning tasks d...

Please sign up or login with your details

Forgot password? Click here to reset