Corpus ID: 31442909

Approximately Optimal Approximate Reinforcement Learning

@inproceedings{Kakade2002ApproximatelyOA,
  title={Approximately Optimal Approximate Reinforcement Learning},
  author={S. Kakade and J. Langford},
  booktitle={ICML},
  year={2002}
}

Topics from this paper

Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence
Stable Policy Optimization via Off-Policy Divergence Regularization
Policy Optimization Through Approximated Importance Sampling
Projections for Approximate Policy Iteration Algorithms
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction
Balancing Safety and Exploration in Policy Gradient
  • 2018
...
1
2
3
4
5
...