Abstract. An adaptive, ergodic cost stochastic control problem for a partially known, semilinear, stochastic system in an infinite dimensional space is formulated and solved. The solutions of the Hamilton-Jacobi-Bellman equations for the discounted cost and the ergodic cost stochastic control problems require some special interpretations because they do not typically exist in the usual sense. The solutions of the parameter dependent ergodic Hamilton-Jacobi-Bellman equations are obtained from some corresponding discounted cost control problems as the discount rate tends to zero. The solutions of the ergodic Hamilton-Jacobi-Bellman equations are shown to depend continuously on the parameter. A certainty equivalence adaptive control is given that is based on the optimal controls from the solutions of the ergodic Hamilton-Jacobi-Bellman equations and a strongly consistent family of estimates of the unknown parameter. This adaptive control is shown to achieve the optimal ergodic cost for the known system. Key words. stochastic adaptive control, ergodic control, stochastic semilinear systems, stochastic optimal control, distributed parameter systems AMS subject classifications. 93C40, 93C20, 60J27, 60H15 some properties of the solution of the Hamilton-JacobiBellman (HJB) equation of optimal control are used to verify self-optimality of an adaptive control using a strongly consistent family of estimates of the unknown parameters. In [17] an almost optimal adaptive control is constructed for a partially known nonlinear stochastic system. To obtain an optimal feedback control in an explicit form, the associated HJB equation must be solved, and for an adaptive control problem, a continuous dependence of the solution of the HJB equation must be verified. Some results for an infinite time horizon discounted cost control problem for a semilinear stochastic system in an infinite dimensional state space are given in [22], where the HJB equation is considered in the mild form, and in [23], where a viscosity solution of the HJB equation is used. Some results for an ergodic cost control problem for a semilinear stochastic system in an infinite dimensional state space are given in [20], where the HJB equation is solved. This is apparently the only result for ergodic cost control for semilinear stochastic systems using the HJB equation. Some other approaches and results for ergodic cost control are given in [16], [18]. For adaptive control, there are results for linear stochastic systems with an ergodic quadratic cost in [13], [14], [15]. Since the results for the discounted cost and the ergodic cost stochastic control problems for known semilinear stochastic systems are relatively recent, it appears that this is the first work on adaptive control for stochastic semilinear systems.