arXiv:1808. 08763v3 Announce Type: replace Abstract: In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem.
arXiv:2606. 10580v1 Announce Type: cross Abstract: The asymptotic behaviour of Monte Carlo optimistic policy iteration (MC-O-PI) is a long-standing open question.
arXiv:2609.06489v1 Announce Type: cross Abstract: Monte Carlo Tree Search (MCTS) has demonstrated success in online planning for deterministic environments, yet significant challenges remain in adapt...
arXiv:2606. 15978v1 Announce Type: new Abstract: Tsitsiklis proved convergence of Monte Carlo optimistic policy iteration under a uniform update structure and identified nonuniform update frequencies as a delicate obstruction.
arXiv:2607. 29593v1 Announce Type: new Abstract: This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equation (SDE) under the continuous-time reinforcement learning framework by Wang et al.
arXiv:2610.00911v1 Announce Type: new Abstract: We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future...
arXiv:2606. 21528v2 Announce Type: replace-cross Abstract: We study first-order methods for solving monotone variational inequalities arising in min-max optimization.
arXiv:2609.39837v1 Announce Type: new Abstract: Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), but existing guarantees often rely on exact or inc...
arXiv:2606. 31769v1 Announce Type: new Abstract: We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds.
arXiv:2603. 23461v2 Announce Type: replace Abstract: We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains linear.
The paper presents DORA, an online learning algorithm for robot navigation that uses Dijkstra’s algorithm as an exact planning engine under a weaker condition than usual causality—specifically, nonnegativity of a reduced cost on a determinized map. DORA calls a shortest‑path oracle a fixed number of times per episode, avoids estimating transition kernels, and incorporates a logarithmic survival weight to keep contact probabilities with dynamic obstacles within a budget. Experiments on grid‑world, directional drilling, and drone surveillance benchmarks show that DORA matches optimistic value iteration with the true transition kernel while performing 4.5 to 19.3 times less planner work, reduces contacts by a factor of seventeen compared to determinize‑and‑replan, and maintains contact rates within wide budget ranges.
arXiv:2411. 01302v2 Announce Type: replace Abstract: We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J.
arXiv:2601. 18840v4 Announce Type: replace Abstract: Markov decision problems are most commonly solved via dynamic programming.