Relative value iteration algorithm with soft state aggregation
From MaRDI portal
A straightforward way to dispel the curse of dimensionality in large stochastic control problems is to replace the lookup table with a generalized function approximator such as state aggregation. The relative value iteration algorithm for average reward Markov decision processes (MDP) with soft state aggregation is investigated. Under a condition of contraction involving a semi-norm, the convergence of the proposed algorithm is proved and an error bound of the approximation is also given.
Recommendations
- Performance Loss Bounds for Approximate Value Iteration with State Aggregation
- Generalized polynomial approximations in Markovian decision processes
- Learning algorithms for Markov decision processes with average cost
- Adaptive aggregation for reinforcement learning in average reward Markov decision processes
- Approximate policy iteration for Markov decision processes via quantitative adaptive aggregations
Cited in
(7)- Reinforcement learning for long-run average cost.
- Revenue management for operations with urgent orders
- Approximate dynamic programming with state aggregation applied to UAV perimeter patrol
- Extreme state aggregation beyond MDPs
- Extreme state aggregation beyond Markov decision processes
- Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
- Performance Loss Bounds for Approximate Value Iteration with State Aggregation
This page was built for publication: Relative value iteration algorithm with soft state aggregation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2705757)
