Pages that link to "Item:Q1784573"

The following pages link to Efficient exploration through active learning for value function approximation in reinforcement learning (Q1784573):

Displaying 9 items.

• Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search (Q553261) (← links)
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation (Q889297) (← links)
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning (Q1784527) (← links)
• Improving importance estimation in pool-based batch active learning for approximate linear regression (Q1942721) (← links)
• Rollout sampling approximate policy iteration (Q2036256) (← links)
• An active exploration method for data efficient reinforcement learning (Q2299097) (← links)
• Reward-weighted regression with sample reuse for direct policy search in reinforcement learning (Q2887009) (← links)
• A parallel scheduling algorithm for reinforcement learning in large state space (Q5964248) (← links)
• Learning under nonstationarity: covariate shift and class-balance change (Q6607922) (← links)