DeepAI AI Chat
Log In Sign Up

Computing Complexity-aware Plans Using Kolmogorov Complexity

by   Elis Stefansson, et al.

In this paper, we introduce complexity-aware planning for finite-horizon deterministic finite automata with rewards as outputs, based on Kolmogorov complexity. Kolmogorov complexity is considered since it can detect computational regularities of deterministic optimal policies. We present a planning objective yielding an explicit trade-off between a policy's performance and complexity. It is proven that maximising this objective is non-trivial in the sense that dynamic programming is infeasible. We present two algorithms obtaining low-complexity policies, where the first algorithm obtains a low-complexity optimal policy, and the second algorithm finds a policy maximising performance while maintaining local (stage-wise) complexity constraints. We evaluate the algorithms on a simple navigation task for a mobile robot, where our algorithms yield low-complexity policies that concur with intuition.


Solving POMDPs by Searching the Space of Finite Policies

Solving partially observable Markov decision processes (POMDPs) is highl...

Confident Approximate Policy Iteration for Efficient Local Planning in q^π-realizable MDPs

We consider approximate dynamic programming in γ-discounted Markov decis...

My Brain is Full: When More Memory Helps

We consider the problem of finding good finite-horizon policies for POMD...

Trustworthy AI for Process Automation on a Chylla-Haase Polymerization Reactor

In this paper, genetic programming reinforcement learning (GPRL) is util...

Teaching a Robot to Walk Using Reinforcement Learning

Classical control techniques such as PID and LQR have been used effectiv...

On Low-Complexity Quickest Intervention of Mutated Diffusion Processes Through Local Approximation

We consider the problem of controlling a mutated diffusion process with ...