Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration

11/03/2022
by   Masood S. Mortazavi, et al.
0

Given an environment (e.g., a simulator) for evaluating samples in a specified design space and a set of weighted evaluation metrics – one can use Theta-Resonance, a single-step Markov Decision Process (MDP), to train an intelligent agent producing progressively more optimal samples. In Theta-Resonance, a neural network consumes a constant input tensor and produces a policy as a set of conditional probability density functions (PDFs) for sampling each design dimension. We specialize existing policy gradient algorithms in deep reinforcement learning (D-RL) in order to use evaluation feedback (in terms of cost, penalty or reward) to update our policy network with robust algorithmic stability and minimal design evaluations. We study multiple neural architectures (for our policy network) within the context of a simple SoC design space and propose a method of constructing synthetic space exploration problems to compare and improve design space exploration (DSE) algorithms. Although we only present categorical design spaces, we also outline how to use Theta-Resonance in order to explore continuous and mixed continuous-discrete design spaces.

READ FULL TEXT
research
07/05/2017

Learning to Design Games: Strategic Environments in Deep Reinforcement Learning

In typical reinforcement learning (RL), the environment is assumed given...
research
10/31/2021

Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method

We discuss the problem of decentralized multi-agent reinforcement learni...
research
04/08/2019

Samples are not all useful: Denoising policy gradient updates using variance

Policy gradient algorithms in reinforcement learning rely on efficiently...
research
02/02/2022

Optimizing Sequential Experimental Design with Deep Reinforcement Learning

Bayesian approaches developed to solve the optimal design of sequential ...
research
08/19/2022

Entropy Augmented Reinforcement Learning

Deep reinforcement learning has gained a lot of success with the presenc...
research
11/23/2019

Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning

Existing automatic 3D image segmentation methods usually fail to meet th...
research
08/16/2022

Solving the Diffusion of Responsibility Problem in Multiagent Reinforcement Learning with a Policy Resonance Approach

SOTA multiagent reinforcement algorithms distinguish themselves in many ...

Please sign up or login with your details

Forgot password? Click here to reset