Research
Scale-free adaptive planning for deterministic dynamics & discounted rewards
arXiv:2604.18312v1 Announce Type: new Abstract: We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value funct
arXiv:2604.18312v1 Announce Type: new Abstract: We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value function is not known, nor are the rewards bounded. We propose Platypoos, a simple scale-free planning algorithm that adapts to the unknown scale and smoothness of the reward function. We provide a sample complexity analysis for Platypoos that improves upon prior work and holds simultaneously over a broad range of discount factors and reward scales, without the algorithm knowing them. We also establish a matching lower bound showing our analysis is optimal up to constants.
Related
- Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets
- Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem
- Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
- Non-Expansive Mappings in Two-Time-Scale Stochastic Approximation: Finite-Time Analysis
- A Modularized Framework for Piecewise-Stationary Restless Bandits
Source: arXiv cs.LG | 2026-04-21