Search Results for author:
Found 7 papers, 2 papers with code
Stochastic Shortest Path with Energy Constraints in POMDPs
Finally, we show experimentally that our algorithm performs well and computes succinct policies on a number of POMDP instances from the literature that were naturally enhanced with energy levels.
Optimizing Expectation with Guarantees in POMDPs (Technical Report)
In this work we go beyond both the "expectation" and "threshold" approaches and consider a "guaranteed payoff optimization (GPO)" problem for POMDPs, where we are given a threshold $t$ and the objective is to find a policy $\sigma$ such that a) each possible outcome of $\sigma$ yields a discounted-sum payoff of at least $t$, and b) the expected discounted-sum payoff of $\sigma$ is optimal (or near-optimal) among all policies satisfying a).
Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-sum Objectives
We consider the expectation optimization with probabilistic guarantee (EOPG) problem, where the goal is to optimize the expectation ensuring that the payoff is above a given threshold with at least a specified probability.
On the Complexity of Value Iteration
We show that, given a horizon $n$ in binary and an MDP, computing an optimal policy is EXP-complete, thus resolving an open problem that goes back to the seminal 1987 paper on the complexity of MDPs by Papadimitriou and Tsitsiklis.
Efficient Strategy Synthesis for MDPs with Resource Constraints
We consider qualitative strategy synthesis for the formalism called consumption Markov decision processes.
Shielding in Resource-Constrained Goal POMDPs
We consider partially observable Markov decision processes (POMDPs) modeling an agent that needs a supply of a certain resource (e. g., electricity stored in batteries) to operate correctly.
Solving Long-run Average Reward Robust MDPs via Stochastic Games
First, we derive new computational complexity bounds for solving long-run average reward polytopic RMDPs, showing for the first time that the threshold decision problem for them is in NP coNP and that they admit a randomized algorithm with sub-exponential expected runtime.
