In the reinforcement learning (RL) system, one important issue is the trade-off problem between exploration and exploitation. In this paper, we studied this dilemma and proposed a new approach to solving this problem by multiple attribute decision-making (MADM). The applicability of the proposed method is extended by transfer learning. The method decomposes a task into several sub-tasks and uses the policies of sub-tasks trained by reinforcement learning. The proposed visual multiple attribute decision-making method (V-MADM) is based on the state-action values of each sub-task to select the action with maximal one. Meanwhile, this work proposes a transfer learning method using a decay function with decreasing probability such that the prior experiences of the sub-tasks can be utilized to accelerate the learning rate. Finally, the experiment of robot confrontation and maze walker is performed to evaluate the learning performance of the proposed method. The experimental results show that fewer training cost is needed to obtain a more effective learning performance.

Reinforcement Learning (RL) agents often encounter the bottleneck of the performance when the dilemma of exploration and exploitation arises. In this study, an adaptive exploration strategy with multi-attribute decision-making is proposed to address the trade-off problem between exploration and exploitation. Firstly, the proposed method decomposes a complex task into several sub-tasks and trains each sub-task using the same training method individually. Then, the proposed method uses a multi-attribute decision-making method to develop an action policy integrating the training results of these trained sub-tasks. There are practical advantages to improve learning performance by allowing multiple learners to learn in parallel. An adaptive exploration strategy determines the probability of exploration depending on the information entropy instead of the suffocating work of empirical tuning. Finally, transfer learning extends the applicability of the proposed method. The experiment of the robot migration, the robot confrontation, and the real wheeled mobile robot are used to demonstrate the availability and practicability of the proposed method.

Multi-Robot Confrontation on physics-based simulators is a complex and time-consuming task, but simulators are required to evaluate the performance of the advanced algorithms. Recently, a few advanced algorithms have been able to produce considerably complex levels in the context of the robot confrontation system when the agents are facing multiple opponents. Meanwhile, the current confrontation decision-making system suffers from difficulties in optimization and generalization. In this paper, a fuzzy reinforcement learning (RL) and the curriculum transfer learning are applied to the micromanagement for robot confrontation system. Firstly, an improved Q-learning in the semi-Markov decision-making process is designed to train the agent and an efficient RL model is defined to avoid the curse of dimensionality. Secondly, a multi-agent RL algorithm with parameter sharing is proposed to train the agents. We use a neural network with adaptive momentum acceleration as a function approximator to estimate the state-action function. Then, a method of fuzzy logic is used to regulate the learning rate of RL. Thirdly, a curriculum transfer learning method is used to extend the RL model to more difficult scenarios, which ensures the generalization of the decision-making system. The experimental results show that the proposed method is effective.

A variety of reinforcement learning (RL) methods are developed to achieve the motion control for the robotic systems, which has been a hot issue. However, the performance of the conventional RL methods often encounters a bottleneck, because the robots have difficulty in choosing an appropriate action in the control task due to the exploration-exploitation dilemma. To address this problem and improve the learning performance, this work introduces an experience aggregative reinforcement learning method with a Multi-Attribute Decision-Making (MADM) to achieve the real-time obstacle avoidance of wheeled mobile robot (WMR). The proposed method employs an experience aggregation method to cluster experiential samples and it can achieve more effective experience storage. Moreover, to achieve the effective action selection using the prior experience, an action selection policy based on a Multi-Attribute Decision-Making is proposed. Inspired by the hierarchical decision-making, this work decomposes the original obstacle avoidance task into two sub-tasks using a divide-and-conquer approach. Each sub-task is trained individually by a double Q-learning using a simple reward function. Each sub-task learns an action policy, which enables the sub-task to selects an appropriate action to achieve a single goal. The standardized rewards of sub-tasks are calculated when fusing these sub-tasks to eliminate differences in rewards for sub-tasks. Then, the proposed method integrates the prior experience of three trained sub-tasks via an action policy based on a MADM to complete the source task. Simulation results show that the proposed method outperforms competitors.