Information-Based Exploration via Random Features for Reinforcement Learning
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
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.
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.
Builds on
23 of 51 references.
Closest ancestors · 4
Same direction, newest first
- 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization16 Dec
- 2024Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning6 Aug
- 2024RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning29 May
- 2024Exploration and Anti-Exploration with Distributional Random Network Distillation18 Jan
Other references · 19
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
- 2018Exploration by Random Network Distillationcited by 993
- 2017Deep Reinforcement Learning that Matterscited by 754
- 2016Deep Exploration via Bootstrapped DQNcited by 527
- 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
- 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
- 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
- 2020Never Give Up: Learning Directed Exploration Strategiescited by 212
- 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
- 2014Learning to Optimize via Information-Directed Samplingcited by 168
- 2024Vanilla Bayesian Optimization Performs Great in High Dimensionscited by 92
7 more
- 2015On the Error of Random Fourier Featurescited by 76
- 2018Efficient Exploration through Bayesian Deep Q-Networkscited by 67
- 2018Information-Directed Exploration for Deep Reinforcement Learningcited by 52
- 2019On Online Learning in Kernelized Markov Decision Processescited by 35
- 2024Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimizationcited by 34
- 2020A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spacescited by 32
- 2019Bayesian Curiosity for Efficient Exploration in Reinforcement Learningcited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
- 2025Value of Information-Enhanced Exploration in Bootstrapped DQN
- 2025Exploration by Random Reward Perturbation
- 2026CIG: Exploration via Conditional Information Gain
- 2024Random Latent Exploration for Deep Reinforcement Learning
- 2026Deep Epistemic Value Functions for Optimistic Exploration
- 2024Effective Exploration Based on the Structural Information Principles
- 2025Sample-efficient and Scalable Exploration in Continuous-Time RL