Provable RL with Exogenous Distractors via Multistep Inverse Dynamics.
Yonathan EfroniDipendra MisraAkshay KrishnamurthyAlekh AgarwalJohn LangfordPublished in: CoRR (2021)
Keyphrases
- inverse dynamics
- reinforcement learning
- nonlinear systems
- parallel manipulator
- autoregressive
- adaptive control
- optimal policy
- function approximation
- model free
- markov decision processes
- state space
- learning algorithm
- input output
- real time
- dynamic model
- optimal control
- fuzzy controller
- rough sets
- object recognition
- machine learning
- neural network