Corpus ID: 59669372

On the sample complexity of reinforcement learning.

@inproceedings{Kakade2003OnTS,
  title={On the sample complexity of reinforcement learning.},
  author={S. Kakade},
  year={2003}
}
This thesis is a detailed investigation into the following question: how much data must an agent collect in order to perform “reinforcement learning” successfully. [...] Key Method We build on the sample based algorithms suggested by Kearns, Mansour, and Ng [2000]. Their sample complexity bounds have no dependence on the size of the state space, an exponential dependence on the planning horizon time, and linear dependence on the complexity of . We suggest novel algorithms with more restricted guarantees whose…Expand
homes.cs.washington.edu
480 Citations
Highly Influential Citations
69
Background Citations
225
Methods Citations
110
Results Citations
16

480 Citations

Citation Type

Citation Type

Reinforcement Learning via Online Linear Regression
Probably Approximately Correct (PAC) Exploration in Reinforcement Learning
  • A. Strehl
  • Mathematics, Computer Science
  • ISAIM
  • 2008
Studying Optimality Bounds for Reinforcement Learning from a KWIK Perspective
  • 2016
Is Q-learning Provably Efficient?
Model-based reinforcement learning with nearly tight exploration complexity bounds
Is Long Horizon RL More Difficult Than Short Horizon RL?
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting
Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal
Model-based reinforcement learning with nearly tight exploration complexity bounds
A Provably Efficient Sample Collection Strategy for Reinforcement Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 80 REFERENCES
Efficient reinforcement learning
Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms
Infinite-Horizon Policy-Gradient Estimation
Learning to Solve Markovian Decision Processes
Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward
Analysis of Some Incremental Variants of Policy Iteration: First Steps Toward Understanding Actor-Cr
Complexity Analysis of Real-Time Reinforcement Learning
Learning Without State-Estimation in Partially Observable Markovian Decision Processes
Approximate Planning in Large POMDPs via Reusable Trajectories
Exploration in Gradient-Based Reinforcement Learning
...
1
2
3
4
5
...