Iterative Value-Aware Model Learning

By Amir-massoud Farahmand. 2018

74 citations recorded by the source corpus.

Subfields: Reinforcement Learning

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

1. Sergey Levine
2. Mohammad Ghavamzadeh
3. Ofir Nachum
4. Yinlam Chow
5. Pieter Abbeel
6. David Silver
7. Satinder Singh
8. Lihong Li

Citations in the corpus

• Control-Aware Representations for Model-based Reinforcement Learning (2020, methodology): “This view of learning control-aware representations is aligned with the value-aware and policy-aware model learning, VAML [Farahmand, 2018] and PAML [Abachi et al.”
• POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning (2020, background): “spirit to our approach is theoretical work on value-aware model learning in RL (Farahmand, 2018).”
• The Value Equivalence Principle for Model-Based Reinforcement Learning (2020, background): “There exist several other criteria to approximate p based on state transitions, such as maximum a posteriori estimation, maximum entropy estimation, and Bayesian posterior inference [13].”