Active reinforcement learning

By Arkady Epshteyn, Adam Vogel, Gerald DeJong. 2008

47 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Management Science and Operations Research, 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 Artificial Intelligence

1. George Dimitri Konidaris
2. Bruno Castro da Silva
3. Andrew Barto
4. Charles Lee Isbell Jr.
5. Andrea Lockerd Thomaz
6. Sebastian Schulze
7. Kaushik Subramanian
8. Owain Evans

In Control and Systems Engineering

1. George Dimitri Konidaris
2. Kaushik Subramanian
3. Charles Lee Isbell Jr.
4. Andrew Barto
5. Bruno Castro da Silva
6. Andrea Lockerd Thomaz
7. Sebastian Schulze
8. Owain Evans

In Management Science and Operations Research

1. Sebastian Schulze
2. Kaushik Subramanian
3. Bruno Castro da Silva
4. Andrea Lockerd Thomaz
5. Andrew Barto
6. George Dimitri Konidaris
7. Charles Lee Isbell Jr.
8. Owain Evans

In Reinforcement Learning

1. George Dimitri Konidaris
2. Bruno Castro da Silva
3. Charles Lee Isbell Jr.
4. Andrew Barto
5. Andrea Lockerd Thomaz
6. Kaushik Subramanian
7. Sebastian Schulze
8. Owain Evans

Citations in the corpus

• Learning Parameterized Skills (2012, methodology): “Other techniques relevant to this work include the Active RL algorithm [22] and the ∆V approach [15].”
• Exploration from Demonstration for Interactive Reinforcement Learning (2016, methodology): “An approach closely related to work presented in this paper is that of Active RL [13] where the authors model the problem as a POMDP.”
• Active Reinforcement Learning with Monte-Carlo Tree Search (2018, background): “An alternative nonBayesian approach is to have the agent learn about the transitions to which the optimal policy is most sensitive (Epshteyn et al., 2008).”