Corpus ID: 219955846

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

@article{Agarwal2020FLAMBESC,
  title={FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs},
  author={Alekh Agarwal and S. Kakade and A. Krishnamurthy and Wen Sun},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.10814}
}
In order to deal with the curse of dimensionality in reinforcement learning (RL), it is common practice to make parametric assumptions where values or policies are functions of some low dimensional feature space. This work focuses on the representation learning question: how can we learn such features? Under the assumption that the underlying (unknown) dynamics correspond to a low rank transition matrix, we show how the representation learning question is related to a particular non-linear… Expand
23 Citations
Logistic $Q$-Learning
Online Sub-Sampling for Reinforcement Learning with General Function Approximation
Online Sparse Reinforcement Learning
Robust Policy Gradient against Strong Data Corruption
Provably Correct Optimization and Exploration with Non-linear Policies
Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms
...
1
2
3
...

References

SHOWING 1-10 OF 65 REFERENCES
Reinforcement Leaning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features
Introduction to Nonparametric Estimation
  • A. Tsybakov
  • Computer Science, Mathematics
  • Springer series in statistics
  • 2009
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
Provably efficient RL with Rich Observations via Latent State Decoding
Stochastic Linear Optimization under Bandit Feedback
Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains
...
1
2
3
4
5
...