
On the Sample Complexity of Reinforcement Learning with Policy Space Generalization
We study the optimal sample complexity in largescale Reinforcement Lear...
read it

Extracting Latent State Representations with Linear Dynamics from Rich Observations
Recently, many reinforcement learning techniques were shown to have prov...
read it

Provably Efficient Qlearning with Function Approximation via Distribution Shift Error Checking Oracle
Qlearning with function approximation is one of the most popular method...
read it

Learning to Guide Random Search
We are interested in derivativefree optimization of highdimensional fu...
read it

Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles
Reinforcement learning (RL) methods have been shown to be capable of lea...
read it

Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations
We consider the demixing problem of two (or more) structured highdimens...
read it

Provably efficient RL with Rich Observations via Latent State Decoding
We study the exploration problem in episodic MDPs with rich observations...
read it
Learning the Linear Quadratic Regulator from Nonlinear Observations
We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a lowdimensional continuous latent state with linear dynamics and quadratic costs, but the agent operates on highdimensional, nonlinear observations such as images from a camera. To enable sampleefficient learning, we assume that the learner has access to a class of decoder functions (e.g., neural networks) that is flexible enough to capture the mapping from observations to latent states. We introduce a new algorithm, RichID, which learns a nearoptimal policy for the RichLQR with sample complexity scaling only with the dimension of the latent state space and the capacity of the decoder function class. RichID is oracleefficient and accesses the decoder class only through calls to a leastsquares regression oracle. Our results constitute the first provable sample complexity guarantee for continuous control with an unknown nonlinearity in the system model and general function approximation.
READ FULL TEXT
Comments
There are no comments yet.