Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees
By Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma. 2018
17 citations recorded by the source corpus.
Subfields: Reinforcement Learning, Statistical Learning Theory
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Ofir Nachum
- Nan Jiang
- Pieter Abbeel
- Aviral Kumar
- Alekh Agarwal
- Shixiang Shane Gu
- George Tucker
In Statistical Learning Theory
- Nan Jiang
- Alekh Agarwal
- Wen Sun
- Akshay Krishnamurthy
- J. Langford
- Marc G. Bellemare
- Doina Precup
- Scott Fujimoto
Citations in the corpus
- DeepMDP: Learning Continuous Latent Space Models for Representation Learning (2019, methodology): “(2) Next Observation Prediction : We train a transition model to predict next observations s 1 „ P p¨| s, a q from the current state representation s s . framework This is similar to model-based RL algorithms which predict future observations (Xu et al., 2018).”
- Off-Policy Deep Reinforcement Learning without Exploration (2018, methodology): “This is used to combat the well-known problems with compounding model errors, and is present in policy search methods (Deisenroth & Rasmussen, 2011; Gal et al., 2016; Higuera et al., 2018; Xu et al., 2018), or combined with trajectory optimization (Chua et al.”
- Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches (2018, background): “Xu et al. (2018) devise a model-based algorithm with function approximation, but their algorithm performs local policy improvement and cannot find a globally optimal policy in a sample-efficient manner.”