Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
نویسندگان
چکیده
We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order O(T ) with an additive term constant yet exponential in some characteristics of the optimal MDP. We propose an algorithm whose regret after T time steps is O( √ T ), with all constants reasonably small. This is optimal in T since O( √ T ) is the optimal regret in the setting of learning in a (single discrete) MDP.
منابع مشابه
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning
We consider a reinforcement learning setting introduced in [6] where the learner does not have explicit access to the states of the underlying Markov decision process (MDP). Instead, she has access to several models that map histories of past interactions to states. Here we improve over known regret bounds in this setting, and more importantly generalize to the case where the models given to th...
متن کاملSelecting the State-Representation in Reinforcement Learning
The problem of selecting the right state-representation in a reinforcement learning problem is considered. Several models (functions mapping past observations to a finite set) of the observations are given, and it is known that for at least one of these models the resulting state dynamics are indeed Markovian. Without knowing neither which of the models is the correct one, nor what are the prob...
متن کاملAdaptive aggregation for reinforcement learning in average reward Markov decision processes
We present an algorithm which aggregates online when learning to behave optimally in an average reward Markov decision process. The algorithm is based on the reinforcement learning algorithm UCRL and uses confidence intervals for aggregating the state space. We derive bounds on the regret our algorithm suffers with respect to an optimal policy. These bounds are only slightly worse than the orig...
متن کاملOnline Regret Bounds for Undiscounted Continuous Reinforcement Learning
We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds for implementing optimism in the face of uncertainty. Beside the existence of an optimal policy which satisfies the Poisson equation, the only assumptions made are Hölder continuity of rewards and transitio...
متن کاملNear-optimal Regret Bounds for Reinforcement Learning Near-optimal Regret Bounds for Reinforcement Learning
This technical report is an extended version of [1]. For undiscounted reinforcement learning in Markov decision processes (MDPs) we consider the total regret of a learning algorithm with respect to an optimal policy. In order to describe the transition structure of an MDP we propose a new parameter: An MDP has diameter D if for any pair of states s, s there is a policy which moves from s to s i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013