On the Importance of Exploration for Real Life Learned Algorithms
Not on the map. Why?
Abstract (arXiv)
The quality of data driven learning algorithms scales significantly with the quality of data available. One of the most straight-forward ways to generate good data is to sample or explore the data source intelligently. Smart sampling can reduce the cost of gaining samples, reduce computation cost in learning, and enable the learning algorithm to adapt to unforeseen events. In this paper, we teach three Deep Q-Networks (DQN) with different exploration strategies to solve a problem of puncturing ongoing transmissions for URLLC messages. We demonstrate the efficiency of two adaptive exploration candidates, variance-based and Maximum Entropy-based exploration, compared to the standard, simple epsilon-greedy exploration approach.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 15 references that are in the map. First posted on arXiv 21 Apr 2023.
Builds on
10 of 15 references.
References · 10
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
- 2015Prioritized Experience Replaycited by 1,099
- 2016Deep Exploration via Bootstrapped DQNcited by 527
- 2019On the Impact of the Activation Function on Deep Neural Networks Trainingcited by 102
- 2021A Survey of Exploration Methods in Reinforcement Learningcited by 73
- 2020Munchausen Reinforcement Learningcited by 69
- 2019Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communicationcited by 21
- 2020Parameterized MDPs and Reinforcement Learning Problems -- A Maximum Entropy Principle Based Frameworkcited by 6
Built on by
Not cited yet.