Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Reinforcement Learning

arXiv:2606.11797 · cs.LG · Submitted 2026-06-10 · Read on arXiv

cs.LG

Submitted: 2026-06-10

Updated: 2026-09-29

Comments: An earlier version (v1) was presented at EIML@ICML2026 (non-archival)

Code: https://github.com/Felix-St/SpaceSampledValueDecay

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Soft Actor-Critic (SAC) — 1× in this paper · explained in 2 episodes

Sources

• A Definition of Non-Stationary Bandits

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