For several classes of reinforcement learning schemes, convergence to action profiles that are not Nash equilibria may occur with positive probability under certain conditions on the payoff function. In this paper, we explore how an alternative reinforcement learning scheme, where the strategy of each agent is also perturbed by a strategy-dependent perturbation (or mutations) function, may excl...

The purpose of reinforcement learning is to maximize rewards from environment, and reinforcement learning agents learn by interacting with external environment through trial and error. Q-Learning, a representative reinforcement learning algorithm, is a type of TD-learning that exploits difference in suitability according to the change of time in learning. The method obtains the optimal policy t...

Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is that a set of decentralized, independent learning automata is able to control a finite Markov Chain with unknown transition probabilities and rewards. This result was recently extended to Markov Games and analyzed with th...

Reinforcement learning is an effective technique for learning action policies in discrete stochastic environments, but its efficiency can decay exponentially with the size of the state space. In many situations significant portions of a large state space may be irrelevant to a specific goal and can be aggregated into a few, relevant, states. The U Tree algorithm generates a tree based state dis...

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge real environments. Many studies have incorporated human knowledge into reinforcement Learning. Though on trajectories often used, could be asked control an A...

This paper proposes a reinforcement fuzzy adaptive learning control network (RFALCON) for solving various reinforcement learning problems. The proposed RFALCON is constructed by integrating two fuzzy adaptive learning control networks (FALCON’S), each of which is a connectionist model with a feedforward multilayer network developed for the realization of a fuzzy controller. One FALCON performs ...

Online model-free reinforcement learning (RL) methods with continuous actions are playing a prominent role when dealing with real-world applications such as Robotics. However, when confronted to non-stationary environments, these methods crucially rely on an exploration-exploitation trade-off which is rarely dynamically and automatically adjusted to changes in the environment. Here we propose a...

This paper presents the results of reinforcement learning experiments for the Robot Auto Racing Simulator (RARS). We compare three different drivers, each taking a different approach to function approximation and reinforcement learning in this continuous-action problem. We report moderate success learning optimal paths around an oval track with simple learners, and we discuss difficulties encou...

L EARNING automata [1] have attracted a considerable interest in the last three decades. They are adaptive decision making devices that operate in unknown stochastic environments and progressively improve their performance via a learning process. They have been initially used by psychologists and biologists to describe the human behavior from both psychological and biological viewpoints. Learni...

This paper proposes a new fuzzy neural network based reinforcement adaptive iterative learning controller for a class of nonlinear systems. Different from some existing reinforcement learning schemes, the reinforcement adaptive iterative learning controller has the advantages of rigorous proofs without using an approximation of the plant Jacobian. The critic is appended into the reinforcement a...