Search Results for author:
Found 17 papers, 4 papers with code
HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanisms
For the partially-informed agent, we propose a continual resolving approach which uses lower bounds, pre-computed offline with heuristic search value iteration (HSVI), instead of opponent counterfactual values.
Learning Algorithms for Verification of Markov Decision Processes
The presented framework focuses on probabilistic reachability, which is a core problem in verification, and is instantiated in two distinct scenarios.
Partially Observable Stochastic Games with Neural Perception Mechanisms
Stochastic games are a well established model for multi-agent sequential decision making under uncertainty.
Safe POMDP Online Planning via Shielding
POMDP online planning algorithms such as Partially Observable Monte-Carlo Planning (POMCP) can solve very large POMDPs with the goal of maximizing the expected return.
Using Reed-Muller Codes for Classification with Rejection and Recovery
When deploying classifiers in the real world, users expect them to respond to inputs appropriately.
Multi-Agent Verification and Control with Probabilistic Model Checking
Probabilistic model checking is a technique for formal automated reasoning about software or hardware systems that operate in the context of uncertainty or stochasticity.
Point-based Value Iteration for Neuro-Symbolic POMDPs
This requires functions over continuous-state beliefs, for which we propose a novel piecewise linear and convex representation (P-PWLC) in terms of polyhedra covering the continuous-state space and value vectors, and extend Bellman backups to this representation.
Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions
This iMDP is, with a user-specified confidence probability, robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples.
Robust Anytime Learning of Markov Decision Processes
Markov decision processes (MDPs) are formal models commonly used in sequential decision-making.
Strategy Synthesis for Zero-Sum Neuro-Symbolic Concurrent Stochastic Games
Second, we introduce two novel representations for the value functions and strategies, constant-piecewise-linear (CON-PWL) and constant-piecewise-constant (CON-PWC) respectively, and propose Minimax-action-free PI by extending a recent PI method based on alternating player choices for finite state spaces to Borel state spaces, which does not require normal-form games to be solved.
Verified Probabilistic Policies for Deep Reinforcement Learning
Deep reinforcement learning is an increasingly popular technique for synthesising policies to control an agent's interaction with its environment.
Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
We use state-of-the-art verification techniques to provide guarantees on the iMDP, and compute a controller for which these guarantees carry over to the autonomous system.
Multi-Objective Controller Synthesis with Uncertain Human Preferences
Complex real-world applications of cyber-physical systems give rise to the need for multi-objective controller synthesis, which concerns the problem of computing an optimal controller subject to multiple (possibly conflicting) criteria.
Canted antiferromagnetic order and spin dynamics in the honeycomb-lattice Tb2Ir3Ga9
Despite the $J_{{\rm eff}}=1/2$ moments, the spin Hamiltonian is denominated by a large in-plane anisotropy $K_z \sim -1$ meV.
Strongly Correlated Electrons Materials Science
Probabilistic Guarantees for Safe Deep Reinforcement Learning
Deep reinforcement learning has been successfully applied to many control tasks, but the application of such agents in safety-critical scenarios has been limited due to safety concerns.
Simultaneous Task Allocation and Planning Under Uncertainty
We propose novel techniques for task allocation and planning in multi-robot systems operating in uncertain environments.
Verification and Control of Partially Observable Probabilistic Real-Time Systems
We then propose techniques to either verify that such a property holds or to synthesise a controller for the model which makes it true.
Logic in Computer Science Systems and Control
