11 papers · 1 filter
Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
Idan Lev-Yehudi, Vadim Indelman
Planning under uncertainty in continuous domains is essential for autonomous systems, yet computationally demanding. Tree-based search methods such as Monte Carlo Tree Search (MCTS…
Action-Gradient Monte Carlo Tree Search for Non-Parametric Continuous (PO)MDPs
Idan Lev-Yehudi, Michael Novitsky, Moran Barenboim +2
Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS) scales effectively via sampling…
Finite-Time Analysis of MCTS in Continuous POMDP Planning
Da Kong, Vadim Indelman
This paper presents a finite-time analysis for Monte Carlo Tree Search (MCTS) in Partially Observable Markov Decision Processes (POMDPs), with probabilistic concentration bounds in…
Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function
Yaacov Pariente, Vadim Indelman
We study risk-sensitive planning under partial observability using the dynamic risk measure Iterated Conditional Value-at-Risk (ICVaR). A policy evaluation algorithm for ICVaR is d…
Online POMDP Planning with Anytime Deterministic Optimality Guarantees
Moran Barenboim, Vadim Indelman
Decision-making under uncertainty is a critical aspect of many practical autonomous systems due to incomplete information. Partially Observable Markov Decision Processes (POMDPs) o…
Online Robust Planning under Model Uncertainty: A Sample-Based Approach
Tamir Shazman, Idan Lev-Yehudi, Ron Benchetit +1
Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for…