No abstract

Actor-critic based on the policy gradient (PG-based AC) methods have been widely studied to solve learning control problems. In order to increase the data efficiency of learning prediction in the critic of PG-based AC, studies on how to use recursive least-squares temporal difference (RLS-TD) algorithms for policy evaluation have been conducted in recent years. In such contexts, the critic RLS-TD evaluates an unknown mixed policy generated by a series of different actors, but not one fixed policy generated by the current actor. Therefore, this AC framework with RLS-TD critic cannot be proved to converge to the optimal fixed point of learning problem. To address the above problem, this paper proposes a new AC framework named critic-iteration PG (CIPG), which learns the state-value function of current policy in an on-policy way and performs gradient ascent in the direction of improving discounted total reward. During each iteration, CIPG keeps the policy parameters fixed and evaluates the resulting fixed policy by -regularized RLS-TD critic. Our convergence analysis extends previous convergence analysis of PG with function approximation to the case of RLS-TD critic. The simulation results demonstrate that the -regularization term in the critic of CIPG is undamped during the learning process, and CIPG has better learning efficiency and faster convergence rate than conventional AC learning control methods.

No abstract

No abstract

The task of learning the value function under a fixed policy in continuous Markov decision processes (MDPs) is considered. Although ELM has fast learning speed and can avoid tuning issues of traditional artificial neural network (ANN), the randomness of the ELM parameters would result in fluctuating performance. In this paper, a least-squares temporal difference algorithm with eligibility traces based on regularized extreme learning machine (RELM-LSTD( )) is proposed to overcome these problems caused by ELM in Reinforcement Learning problem. The proposed algorithm combined the LSTD( ) algorithm with RELM. The RELM is used to approximate value functions. Furthermore, the eligibility trace term is introduced to increase data efficiency. In experiments, the performances of the proposed algorithm are demonstrated and compared with those of LSTD and ELM-LSTD. Experiment results show that the proposed algorithm can achieve a more stable and better performance in approximating the value function under a fixed policy.

No abstract

No abstract

No abstract