Pages that link to "Item:Q2833114"
From MaRDI portal
The following pages link to Robust MDPs with \(k\)-rectangular uncertainty (Q2833114):
Displaying 13 items.
- Robust decomposable Markov decision processes motivated by allocating school budgets (Q297098) (← links)
- Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes (Q2026970) (← links)
- A survey of decision making and optimization under uncertainty (Q2241216) (← links)
- Reinforcement learning in robust Markov decision processes (Q2833106) (← links)
- Concurrent MDPs with Finite Markovian Policies (Q5014502) (← links)
- (Q5053310) (← links)
- Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets (Q5081099) (← links)
- Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity (Q5147037) (← links)
- Infinite Horizon Average Cost Dynamic Programming Subject to Total Variation Distance Ambiguity (Q5232245) (← links)
- A family of \(s\)-rectangular robust MDPs: relative conservativeness, asymptotic analyses, and finite-sample properties (Q6495779) (← links)
- A dynamical neural network approach for distributionally robust chance-constrained Markov decision process (Q6564772) (← links)
- Robust \(Q\)-learning algorithm for Markov decision processes under Wasserstein uncertainty (Q6605954) (← links)
- Set-based value operators for non-stationary and uncertain Markov decision processes (Q6659261) (← links)
