Search Results for author:
Found 7 papers, 0 papers with code
Conformal Off-Policy Prediction for Multi-Agent Systems
In this work, we introduce MA-COPP, the first conformal prediction method to solve OPP problems involving multi-agent systems, deriving joint prediction regions for all agents' trajectories when one or more "ego" agents change their policies.
Counterfactual Influence in Markov Decision Processes
Our work addresses a fundamental problem in the context of counterfactual inference for Markov Decision Processes (MDPs).
Assume-Guarantee Reinforcement Learning
We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel.
Causal Temporal Reasoning for Markov Decision Processes
We introduce $\textit{PCFTL (Probabilistic CounterFactual Temporal Logic)}$, a new probabilistic temporal logic for the verification of Markov Decision Processes (MDP).
Compositional Reinforcement Learning for Discrete-Time Stochastic Control Systems
A key contribution is to leverage the convergence results for adversarial RL (minimax Q-learning) on finite stochastic arenas to provide control strategies maximizing the probability of satisfaction over the network of continuous-space systems.
Data-Driven Abstraction-Based Control Synthesis
The growth bound together with the sampled trajectories are then used to construct the abstraction and synthesise a controller.
Formal Policy Synthesis for Continuous-Space Systems via Reinforcement Learning
We use this procedure to guide the RL algorithm towards a policy that converges to an optimal policy under suitable assumptions on the process.
