Decision Tree Function Approximation in Reinforcement Learning
نویسندگان
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
Reinforcement Learning with Decision Trees
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 funct...
متن کاملComputer Science Technical Report Decision Tree Function Approximation in Reinforcement Learning
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 funct...
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 کاملTransfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling
In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a new incremental relational regression tree algorithm that is capable of dealing with concept drift through tree restructuring and show that it enables a reinforcement learner, more precisely a Q-learner, to transfer kn...
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 کامل