An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies
Preprint
Abstract
What is a good exploration strategy for an agent that interacts with an environment in the absence of external rewards? Ideally, we would like to get a policy driving towards a uniform state-action visitation (highly exploring) in a minimum number of steps (fast mixing), in order to ease efficient learning of any goal-conditioned policy later on. Unfortunately, it is remarkably arduous to directly learn an optimal policy of this nature. In this paper, we propose a novel surrogate objective for learning highly exploring and fast mixing policies, which focuses on maximizing a lower bound to the entropy of the steady-state distribution induced by the policy. In particular, we introduce three novel lower bounds, that lead to as many optimization problems, that tradeoff the theoretical guarantees with computational complexity. Then, we present a model-based reinforcement learning algorithm, IDE$^{3}$AL, to learn an optimal policy according to the introduced objective. Finally, we provide an empirical evaluation of this algorithm on a set of hard-exploration tasks.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Mastering the game of Go without human knowledgeNature, 2017
- What is intrinsic motivation? A typology of computational approachesFrontiers in Neurorobotics, 2007
- Column sums and the conditioning of the stationary distribution for a stochastic matrixOperators and Matrices, 2007
- Context tree estimation for not necessarily finite memory processes, via BIC and MDLIEEE Transactions on Information Theory, 2006
- Fastest Mixing Markov Chain on a GraphSIAM Review, 2004