Reinforcement Learning with Decision Trees
نویسنده
چکیده
We present a decision tree based approach to function approximation in reinforcement learning. We compare our approach with table lookup and a neural network function approximator on three problems: the well known mountain car and pole balance problems as well as a simulated automobile race car. We find that the decision tree can provide better learning performance than the neural network function approximation and can solve large problems that are infeasible using table lookup.
منابع مشابه
A Reinforcement Learning Approach to Online Learning of Decision Trees
Online decision tree learning algorithms typically examine all features of a new data point to update model parameters. We propose a novel alternative, Reinforcement Learningbased Decision Trees (RLDT), that uses Reinforcement Learning (RL) to actively examine a minimal number of features of a data point to classify it with high accuracy. Furthermore, RLDT optimizes a long term return, providin...
متن کاملGeneration of regression trees using reinforcement learning
We present a novel methodology for regression trees generation that uses the reinforcement learning frame for learning efficient regression trees. We describe the basic variant of such a methodology that uses the Monte-Carlo method to explore the space of possible regression trees. Comparison with other methods of regression is performed and evaluated. Our algorithm is implemented as a software...
متن کاملConvergence of reinforcement learning using a decision tree learner
In this paper, we propose conditions under which Q iteration using decision trees for function approximation is guaranteed to converge to the optimal policy in the limit, using only a storage space linear in the size of the decision tree. We analyze different factors that influence the efficiency of the proposed algorithm, and in particular study the efficiency of different concept languages. W...
متن کاملAdaptive Building of Decision Trees by Reinforcement Learning
Decision tree learning represents a well known family of inductive learning algorithms that are able to extract, from the presented training sets, classification rules whose preconditions can be represented as disjunctions of conjunctions of constraints. The name of decision trees is due to the fact that the preconditions can be represented as a tree where each node is a constraint and each pat...
متن کاملMultivariate Decision Tree Function Approximation for Reinforcement Learning
In reinforcement learning, when dimensionality of the state space increases, making use of state abstraction seems inevitable. Among the methods proposed to solve this problem, decision tree based methods could be useful as they provide automatic state abstraction. But existing methods use univariate, therefore axis-aligned, splits in decision nodes, imposing hyper-rectangular partitioning of t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003