# On the Importance of Exploration for Real Life Learned Algorithms

arXiv: https://arxiv.org/abs/2304.10860 · HTML: https://mlsanity.com/paper/2304.10860/

## 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 (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [On the Impact of the Activation Function on Deep Neural Networks Training](https://mlsanity.com/paper/1902.06853/) (2019)
- [A Survey of Exploration Methods in Reinforcement Learning](https://mlsanity.com/paper/2109.00157/) (2021)
- [Munchausen Reinforcement Learning](https://mlsanity.com/paper/2007.14430/) (2020)
- [Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication](https://mlsanity.com/paper/1911.03264/) (2019)
- [Parameterized MDPs and Reinforcement Learning Problems -- A Maximum Entropy Principle Based Framework](https://mlsanity.com/paper/2006.09646/) (2020)

## 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.