Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

NIPS 2020, 2020.

Cited by: 0|Views121
EI
Weibo:
The standard formulation for reinforcement learning with partial observability is the Partially Observable Markov Decision Process, in which an agent operating on noisy observations makes decisions that influence the evolution of a latent state

Abstract:

Partial observability is a common challenge in many reinforcement learning applications, which requires an agent to maintain memory, infer latent states, and integrate this past information into exploration. This challenge leads to a number of computational and statistical hardness results for learning general Partially Observable Marko...More

Code:

Data:

Your rating :
0

 

Tags
Comments