arXiv AI
Jul 17
Decision Making Needs Uncertainty Quantification [Lecture Notes]
arXiv:2607. 14407v1 Announce Type: cross Abstract: Many signal processing systems ultimately exist to {act}.
Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making
arXiv:2607. 04019v1 Announce Type: cross Abstract: Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use.
Related stories
arXiv Machine Learning
Jul 21
Distributional Soft Bellman Operator under the Cram\'er Geometry
arXiv:2607. 17897v1 Announce Type: new Abstract: Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the policy evaluation step is governed by a distributional soft Bellman operator acting on entropy-regularised returns.
arXiv Machine Learning
Jun 24
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
arXiv:2603. 08287v2 Announce Type: replace-cross Abstract: We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm.
arXiv Machine Learning
Jun 11
Reinforcement Learning with Action-Triggered Observations
arXiv:2510. 02149v2 Announce Type: replace Abstract: We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a reinforcement learning framework for partial observability in which full state observations occur stochastically at each step, with probability determined by the chosen action.
arXiv Machine Learning
Aug 10
Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions
arXiv:2608. 06545v1 Announce Type: new Abstract: Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.
arXiv Machine Learning
Jun 9
Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
arXiv:2605. 26078v3 Announce Type: replace Abstract: Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions.
arXiv Machine Learning
Jun 4
Bayesian learning for the stochastic shortest path problem
arXiv:2606. 04845v1 Announce Type: cross Abstract: Sequential decision-making problems are often modelled as a Markov decision process (MDP).
arXiv Machine Learning
Jul 30
Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes
arXiv:2607. 27132v1 Announce Type: new Abstract: An agent acting under partial observability must retain a recursively updateable statistic of history that restores the Markov property, but the smallest such statistic is generally unknown.
arXiv AI
Jun 10
Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
arXiv:2606. 09858v1 Announce Type: cross Abstract: Robust decision-making requires compression.
arXiv Machine Learning
Jul 22
Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
arXiv:2607. 18554v1 Announce Type: cross Abstract: We develop the Continuous Distributed Coupled Policy Gradient (CDCPG) algorithm for cooperative reinforcement learning in networked Markov decision processes with continuous state and action spaces.
arXiv AI
Jul 22
Toward Learning POMDPs Beyond Full-Rank Actions and State Observability
arXiv:2601. 18930v4 Announce Type: replace-cross Abstract: We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms.
arXiv Machine Learning
Jun 29
PAC-Bayesian Certificates for Quadratic Closed-Loop Control
arXiv:2606. 28281v1 Announce Type: cross Abstract: PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective is a quadratic trajectory cost.