arXiv Machine Learning
A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 29
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
arXiv:2512. 23075v5 Announce Type: replace-cross Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$.
arXiv Machine Learning
Jun 19
Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL
arXiv:2605. 05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy.
arXiv Machine Learning
Aug 17
Offline Deep Q* Estimation with Diffusion Models
arXiv:2608. 14401v1 Announce Type: cross Abstract: In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations.
arXiv Machine Learning
Aug 21
Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic
arXiv:2608. 19587v1 Announce Type: new Abstract: While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the unregularized objective remains underexplored.
arXiv Statistics ML
Sep 2
Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
arXiv:2511.08097v2 Announce Type: replace-cross Abstract: We consider a general infinite horizon Heterogeneous Restless multi-armed Bandit (RMAB). Heterogeneity is a fundamental problem for many real...
Hugging Face Trending Papers
Aug 20
Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic
While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the unregularized objective remains underexplored. Existing analyses often rely on double-loop architectures and invoke a linear entropy penalty.