An Experts Algorithm for Transfer Learning

52 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Disentangling Transfer in Continual Reinforcement Learning (2022, methodology): “[41, 50, 42, 39] present methods on how to ﬁnd and use mappings between different domains.”
Transfer Learning for Reinforcement Learning Domains: A Survey (2009, background): “No further learning is done in thetarg t task, but the transferred value functions perform better than a handcoded strategy provided by the authors, despite having additional friendly and adversarial agents.”
Transfer learning for reinforcement learning on a physical robot (2010, background): “Singh [13] also explored this area, naming it " compositional learning.”
Transfer Learning via Inter-Task Mappings for Temporal Difference Learning (2007, methodology): “AtEase (Talvitie and Singh, 2007) is an algorithm that generates a number of possible state-feature mappings and then uses a multi-armed bandit approach to select the best mapping.”
Autonomous transfer for reinforcement learning (2008, background): “[15] V. Soni and S. Singh.”
Automatically Mapped Transfer between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines (2013, background): “For example, semantic knowledge about state features between two tasks may be used [8,10], background knowledge about the range or type of state variables can be used [14,19], or transition models for each possible mapping could be generated and tested [16].”