Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms

02/10/2021
by   Arash Mahyari, et al.
0

Despite advancements in deep reinforcement learning algorithms, developing an effective exploration strategy is still an open problem. Most existing exploration strategies either are based on simple heuristics, or require the model of the environment, or train additional deep neural networks to generate imagination-augmented paths. In this paper, a revolutionary algorithm, called Policy Augmentation, is introduced. Policy Augmentation is based on a newly developed inductive matrix completion method. The proposed algorithm augments the values of unexplored state-action pairs, helping the agent take actions that will result in high-value returns while the agent is in the early episodes. Training deep reinforcement learning algorithms with high-value rollouts leads to the faster convergence of deep reinforcement learning algorithms. Our experiments show the superior performance of Policy Augmentation. The code can be found at: https://github.com/arashmahyari/PolicyAugmentation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2018

Off-Policy Deep Reinforcement Learning without Exploration

Reinforcement learning traditionally considers the task of balancing exp...
research
06/20/2022

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

Massive practical works addressed by Deep Q-network (DQN) algorithm have...
research
10/12/2019

Efficient Inference and Exploration for Reinforcement Learning

Despite an ever growing literature on reinforcement learning algorithms ...
research
07/21/2021

MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments

This paper is an initial endeavor to bridge the gap between powerful Dee...
research
03/05/2019

Viewpoint Optimization for Autonomous Strawberry Harvesting with Deep Reinforcement Learning

Autonomous harvesting may provide a viable solution to mounting labor pr...
research
02/17/2023

Deep Reinforcement Learning for mmWave Initial Beam Alignment

We investigate the applicability of deep reinforcement learning algorith...
research
11/16/2021

CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms

CleanRL is an open-source library that provides high-quality single-file...

Please sign up or login with your details

Forgot password? Click here to reset