# Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control

arXiv: https://arxiv.org/abs/2508.13922 · HTML: https://mlsanity.com/paper/2508.13922/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 29 of 29)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Distributed Distributional Deterministic Policy Gradients](https://mlsanity.com/paper/1804.08617/) (2018)
- [Goal-Conditioned Reinforcement Learning with Imagined Subgoals](https://mlsanity.com/paper/2107.00541/) (2021)
- [Discovering and Achieving Goals via World Models](https://mlsanity.com/paper/2110.09514/) (2021)
- [Variational Option Discovery Algorithms](https://mlsanity.com/paper/1807.10299/) (2018)
- [Action Branching Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1711.08946/) (2017)
- [Discretizing Continuous Action Space for On-Policy Optimization](https://mlsanity.com/paper/1901.10500/) (2019)
- [Learning Robot Skills with Temporal Variational Inference](https://mlsanity.com/paper/2006.16232/) (2020)
- [Learning Awareness Models](https://mlsanity.com/paper/1804.06318/) (2018)
- [Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills](https://mlsanity.com/paper/2310.19424/) (2023)

## Abstract (arXiv)

A policy in deep reinforcement learning (RL), either deterministic or stochastic, is commonly parameterized as a Gaussian distribution alone, limiting the learned behavior to be unimodal. However, the nature of many practical decision-making problems favors a multimodal policy that facilitates robust exploration of the environment and thus to address learning challenges arising from sparse rewards, complex dynamics, or the need for strategic adaptation to varying contexts. This issue is exacerbated in continuous control domains where exploration usually takes place in the vicinity of the predicted optimal action, either through an additive Gaussian noise or the sampling process of a stochastic policy. In this paper, we introduce Categorical Policies to model multimodal behavior modes with an intermediate categorical distribution, and then generate output action that is conditioned on the sampled mode. We explore two sampling schemes that ensure differentiable discrete latent structure while maintaining efficient gradient-based optimization. By utilizing a latent categorical distribution to select the behavior mode, our approach naturally expresses multimodality while remaining fully differentiable via the sampling tricks. We evaluate our multimodal policy on a set of DeepMind Control Suite environments, demonstrating that through better exploration, our learned policies converge faster and outperform standard Gaussian policies. Our results indicate that the Categorical distribution serves as a powerful tool for structured exploration and multimodal behavior representation in continuous control.