Finite-time bounds for fitted value iteration
From MaRDI portal
Recommendations
- Performance Bounds in $L_p$‐norm for Approximate Value Iteration
- Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
- Factored value iteration converges
- Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
- Finite-sample analysis of least-squares policy iteration
Cited in
(57)- Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
- Adaptive-resolution reinforcement learning with polynomial exploration in deterministic domains
- A linear programming methodology for approximate dynamic programming
- Solving dynamic discrete choice models using smoothing and sieve methods
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics
- Batch policy learning in average reward Markov decision processes
- Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
- Fitted Q-iteration by functional networks for control problems
- Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
- Efficient approximate dynamic programming based on design and analysis of computer experiments for infinite-horizon optimization
- Empirical dynamic programming
- A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
- A novel use of value iteration for deriving bounds for threshold and switching curve optimal policies
- Fitted value function iteration with probability one contractions
- Factored value iteration converges
- Batch mode reinforcement learning based on the synthesis of artificial trajectories
- Convergence of Recursive Stochastic Algorithms Using Wasserstein Divergence
- Mean-field controls with Q-learning for cooperative MARL: convergence and complexity analysis
- Dynamic programming deconstructed: transformations of the Bellman equation and computational efficiency
- Some limit properties of Markov chains induced by recursive stochastic algorithms
- Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
- Performance Loss Bounds for Approximate Value Iteration with State Aggregation
- Finite-sample analysis of least-squares policy iteration
- Quadratic approximate dynamic programming for input-affine systems
- Performance Bounds in $L_p$‐norm for Approximate Value Iteration
- Learning when-to-treat policies
- Analyzing approximate value iteration algorithms
- A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
- Variational actor-critic algorithms,
- Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning
- Optimal policy evaluation using kernel-based temporal difference methods
- Generalized fitted Q-iteration with clustered data
- The central role of the loss function in reinforcement learning
- Offline reinforcement learning in large state spaces: algorithms and guarantees
- On the statistical complexity for offline and low-adaptive reinforcement learning with structures
- Sample-based planning and learning with function approximation
- Risk and optimal policies in bandit experiments
- Error analysis for approximate CVaR-optimal control with a maximum cost
- An L^2 analysis of reinforcement learning in high dimensions with kernel and neural network approximation
- Robust value iteration for optimal control of discrete-time linear systems
- Fitted value iteration methods for bicausal optimal transport
- Testing stationarity and change point detection in reinforcement learning
- Perturbational complexity by distribution mismatch: a systematic analysis of reinforcement learning in reproducing kernel Hilbert space
- Deep approximate policy iteration
- Dynamic programs on partially ordered sets
- Online learning with off-policy feedback
- Variance-reduced conservative policy iteration
- Almost optimal algorithms for two-player zero-sum linear mixture Markov games
- Data-Driven Knowledge Transfer in Batch Q * Learning
- An offline risk-aware policy selection method for Bayesian Markov decision processes
- A review of off-policy evaluation in reinforcement learning
- Distributional Off-Policy Evaluation with Deep Quantile Process Regression
- Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy
- Simulation-based dynamic optimization for ambulance dispatch and casualty distribution in mass casualty incident
- A convex optimization approach to dynamic programming in continuous state and action spaces
- Approximate dynamic programming with a fuzzy parameterization
This page was built for publication: Finite-time bounds for fitted value iteration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3096132)
