Deep Epistemic Value Functions for Optimistic Exploration
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/LeanderDiazBone/devote
Sources
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Minimax Regret Bounds for Reinforcement Learning
- Layer Normalization
- Unifying Count-Based Exploration and Intrinsic Motivation
- UCB Exploration via Q-Ensembles
- Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
- Better Exploration with Optimistic Actor-Critic
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
- Challenges of Real-World Reinforcement Learning
- Hypermodels for Exploration
- Go-Explore: a New Approach for Hard-Exploration Problems
- 'In-Between' Uncertainty in Bayesian Neural Networks
- Noisy Networks for Exploration
- Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
- Mastering Diverse Domains through World Models
- Deep Reinforcement Learning and the Deadly Triad
- Information Directed Sampling and Bandits with Heteroscedastic Noise
- Probabilistic Artificial Intelligence
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks