Off-policy evaluation for MDPs with unknown structure

By Assaf Hallak, François Schnitzler, Timothy A. Mann, Shie Mannor. 2015

7 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. Abhishek Gupta
3. Chelsea Finn
4. Ashvin Nair
5. Pieter Abbeel
6. Murtaza Dalal
7. Vikash Kumar
8. Shixiang Shane Gu

Citations in the corpus

• Accelerating Online Reinforcement Learning with Offline Datasets (2020, methodology): “due to error accumulation with distribution shift [8, 21]. Offline RL methods aim to address this issue, often by constraining the actor updates to avoid excessive deviation from the data distribution [23, 41, 13, 14, 12, 21, 8, 22, 38, 26, 47]. One class of these methods utilize importance sampling ”
• Safe Reinforcement Learning (2015, background): “This approach can be particularly powerful if some structure of the environment is known a priori (Hallak et al., 2015).”