# The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective

arXiv: https://arxiv.org/abs/2408.09974 · HTML: https://mlsanity.com/paper/2408.09974/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Count-Based Exploration with Neural Density Models](https://mlsanity.com/paper/1703.01310/) (2017)
- [Self-Imitation Learning](https://mlsanity.com/paper/1806.05635/) (2018)
- [Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices](https://mlsanity.com/paper/2008.02790/) (2020)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)
- [Improving Intrinsic Exploration with Language Abstractions](https://mlsanity.com/paper/2202.08938/) (2022)
- [Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning](https://mlsanity.com/paper/2402.04080/) (2024)
- [A Max-Min Entropy Framework for Reinforcement Learning](https://mlsanity.com/paper/2106.10517/) (2021)
- [Latent World Models For Intrinsically Motivated Exploration](https://mlsanity.com/paper/2010.02302/) (2020)
- [Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2101.09458/) (2021)
- [LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework](https://mlsanity.com/paper/2310.03342/) (2023)
- [Entropy Regularized Reinforcement Learning Using Large Deviation Theory](https://mlsanity.com/paper/2106.03931/) (2021)

## Built on by (most cited first, 5 of 5)

- [Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?](https://mlsanity.com/paper/2605.15855/) (2026)
- [Pixel-Space Diffusion Transformers](https://mlsanity.com/paper/2607.17585/) (2026)
- [Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models](https://mlsanity.com/paper/2608.06768/) (2026)
- [Cavity Duplexer Tuning with 1d Resnet-like Neural Networks](https://mlsanity.com/paper/2510.15796/) (2025)
- [PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model](https://mlsanity.com/paper/2608.06794/) (2026)

## Abstract (arXiv)

The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces learning efficiency, while over-dependence on exploitation might trap agents in local optima. This paper revisits the exploration-exploitation dilemma from the perspective of entropy by revealing the relationship between entropy and the dynamic adaptive process of exploration and exploitation. Based on this theoretical insight, we establish an end-to-end adaptive framework called AdaZero, which automatically determines whether to explore or to exploit as well as their balance of strength. Experiments show that AdaZero significantly outperforms baseline models across various Atari and MuJoCo environments with only a single setting. Especially in the challenging environment of Montezuma, AdaZero boosts the final returns by up to fifteen times. Moreover, we conduct a series of visualization analyses to reveal the dynamics of our self-adaptive mechanism, demonstrating how entropy reflects and changes with respect to the agent's performance and adaptive process.