# Information-Based Exploration via Random Features for Reinforcement Learning

arXiv: https://arxiv.org/abs/2607.17981 · HTML: https://mlsanity.com/paper/2607.17981/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## 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, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [(More) Efficient Reinforcement Learning via Posterior Sampling](https://mlsanity.com/paper/1306.0940/) (2013)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [Finite-Time Analysis of Kernelised Contextual Bandits](https://mlsanity.com/paper/1309.6869/) (2013)
- [Learning to Optimize via Information-Directed Sampling](https://mlsanity.com/paper/1403.5556/) (2014)
- [Vanilla Bayesian Optimization Performs Great in High Dimensions](https://mlsanity.com/paper/2402.02229/) (2024)
- [On the Error of Random Fourier Features](https://mlsanity.com/paper/1506.02785/) (2015)
- [Efficient Exploration through Bayesian Deep Q-Networks](https://mlsanity.com/paper/1802.04412/) (2018)
- [Information-Directed Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1812.07544/) (2018)
- [On Online Learning in Kernelized Markov Decision Processes](https://mlsanity.com/paper/1911.01871/) (2019)
- [Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization](https://mlsanity.com/paper/2402.02746/) (2024)
- [Exploration and Anti-Exploration with Distributional Random Network Distillation](https://mlsanity.com/paper/2401.09750/) (2024)
- [A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces](https://mlsanity.com/paper/2007.05078/) (2020)
- [MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization](https://mlsanity.com/paper/2412.12098/) (2024)
- [Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning](https://mlsanity.com/paper/2408.03029/) (2024)
- [RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning](https://mlsanity.com/paper/2405.19548/) (2024)
- [Bayesian Curiosity for Efficient Exploration in Reinforcement Learning](https://mlsanity.com/paper/1911.08701/) (2019)

## Abstract (arXiv)

Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes algorithms more complex and theoretical guarantees harder to establish. We introduce Random Feature Information Gain (RFIG), grounded in Bayesian kernel methods theory, which uses random Fourier features to approximate information gain and compute exploration bonuses in non-countable spaces. We provide error bounds on information gain approximation and avoid the black-box aspects of neural network-based uncertainty estimation, for optimism-based exploration. We present practical details that make RFIG scalable to deep RL scenarios, enabling smooth integration into standard deep RL algorithms. Experimental evaluation across diverse control and navigation tasks demonstrates that RFIG achieves competitive performance with well-established deep exploration methods while offering superior theoretical interpretation.