Meta-learning optimal parameter values in non-stationary environments

Many learning and heuristic search algorithms require tuning of parameters to achieve optimum performance. In stationary and deterministic problem domains this is usually achieved through off-line sensitivity analysis. However, this method breaks down in non-stationary and non-deterministic environments, where the optimal set of values for the parameters keep changing over time. What is needed in such scenarios is a meta-learning (ML) mechanism that can learn the optimal set of parameters on-line while the learning algorithm is trying to learn its target concept. In this paper, we present a simple meta-learning algorithm to learn the temperature parameter of the Softmax reinforcement-learning (RL) algorithm. We present results to show the efficacy of this meta-learning algorithm in two domains.