Hierarchical actor-critic with hindsight for mobile robot with continuous state space

Hierarchies are used in reinforcement learning to increase learning speed in sparse reward tasks. In this kind of tasks, the main problem is elapsed time, required for the initial policy to reach the goal during the first steps. Hierarchies can split a problem into a set of subproblems that could be reached in less time. In order to implement this idea, Hierarchical Reinforcement Learning (HRL) algorithms need to be able to learn the multiple levels within a hierarchy in parallel, so these smaller subproblems could be solved at the same time. Most famous existing HRL algorithms that can learn multi-level hierarchies are not able to efficiently learn levels of policies simultaneously, especially in continuous space and action space environment. To address this problem, we had analyzed the newest existing framework, Hierarchical Actor-Critic with Hindsight (HAC), test it in the simulated mobile robot environment and determine the optimal configuration of parameters and ways to encode information about the environment states.