The following pages link to Natural actor-critic algorithms (Q1049136):
Displayed 18 items.
- A constrained optimization perspective on actor-critic algorithms and application to network routing (Q286519) (← links)
- Multiscale Q-learning with linear function approximation (Q312650) (← links)
- An online actor-critic algorithm with function approximation for constrained Markov decision processes (Q438776) (← links)
- Autonomous reinforcement learning with experience replay (Q461126) (← links)
- Parameterized Markov decision process and its application to service rate control (Q492972) (← links)
- Hessian matrix distribution for Bayesian policy gradient reinforcement learning (Q545311) (← links)
- The Borkar-Meyn theorem for asynchronous stochastic approximations (Q553371) (← links)
- An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes (Q616967) (← links)
- The factored policy-gradient planner (Q835832) (← links)
- Reinforcement learning algorithms with function approximation: recent advances and applications (Q903601) (← links)
- Natural actor-critic algorithms (Q1049136) (← links)
- An incremental off-policy search in a model-free Markov decision process using a single sample path (Q1621868) (← links)
- Variance-constrained actor-critic algorithms for discounted and average reward MDPs (Q1689603) (← links)
- Real-time reinforcement learning by sequential actor-critics and experience replay (Q1784532) (← links)
- Preference-based reinforcement learning: a formal framework and a policy iteration algorithm (Q1945130) (← links)
- A stability criterion for two timescale stochastic approximation schemes (Q2409333) (← links)
- Adaptive critic design with graph Laplacian for online learning control of nonlinear systems (Q2795795) (← links)
- Actor-Critic Algorithms with Online Feature Adaptation (Q5270681) (← links)