The paper introduces an approximate policy‑iteration algorithm for finite‑horizon zero‑sum partially observable stochastic games (zs‑POSGs). It maintains a separate policy for each player and updates both jointly using conservative policy updates along occupancy trajectories, avoiding the need to approximate a full central value function. The method focuses computation on occupancy regions where the current joint policy can be exploited, and shows competitive performance on small horizons while improving the runtime‑exploitability trade‑off at larger horizons compared to existing solvers such as PBVI, HSVI, and CFR+.
arXiv:2609.35874v1 Announce Type: new Abstract: Online POMDP planners optimize the expected cumulative cost, which can mask dangerous states when the belief places significant mass on high-cost state...
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: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:2610.08384v1 Announce Type: new Abstract: In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT con...
In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT conditions of the Bellman equation and require solvi...
The paper introduces Planning Under Noise (PUN), a neural operator that learns noise‑aware value fields for planning in unseen geometries. By imposing reflecting Neumann conditions on obstacles and a Dirichlet condition at the goal, PUN allows sampled paths to explore free space until reaching the target. It extends the Monte Carlo solver Walk on Stars to higher dimensions, learns geometry‑to‑field mappings from noisy labels, and achieves high success rates and low runtimes on 4‑D replanning benchmarks across multiple noise levels.
arXiv:2607. 05359v1 Announce Type: new Abstract: Planning under uncertainty in continuous domains is essential for autonomous systems, yet computationally demanding.
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...
arXiv:2606. 23995v1 Announce Type: cross Abstract: Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games.
arXiv:2606. 29169v1 Announce Type: cross Abstract: Many important games have more than two players and imperfect information.
NashDreamer is a new model-based reinforcement learning framework designed for two-player zero-sum imperfect-information games. It introduces a centralized Multi-Agent Recurrent State-Space Model that separates environment dynamics from player strategy effects, enabling the use of any policy gradient algorithm while preserving convergence guarantees to Nash equilibria. Experiments on four benchmark games show that NashDreamer achieves significantly better sample efficiency than model-free baselines early in training, and the authors analyze its optimization landscape, noting a potential vulnerability to posterior collapse in stochastic settings.
arXiv:2610.15461v1 Announce Type: new Abstract: MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through...