From pixels to policies: A bootstrapping agent

By Jeremy Stober, Benjamin Kuipers. 2008

27 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, 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. Marc G. Bellemare
2. Michael H. Bowling
3. Sergey Levine
4. Joel Veness
5. Pieter Abbeel
6. David Silver
7. Joelle Pineau
8. R´emi Munos

In Cognitive Neuroscience

1. Marc G. Bellemare
2. Joel Veness
3. Richard M. Murray
4. Andrea Censi
5. Samuel Wintermute
6. Sergey Levine
7. Pieter Abbeel

In Reinforcement Learning

1. Marc G. Bellemare
2. Michael H. Bowling
3. Joel Veness
4. Sergey Levine
5. Pieter Abbeel
6. R´emi Munos
7. David Silver
8. Joelle Pineau

Citations in the corpus

• The Arcade Learning Environment: An Evaluation Platform for General Agents (2012, background): “Similar ideas have been developed around the theme of lifelong learning : learning a reusable, highlevel understanding of the world from raw sensory data (Thrun & Mitchell, 1995; Pierce & Kuipers, 1997; Stober & Kuipers, 2008; Sutton et al., 2011).”
• DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics (2020, unknown): “Later works focus on the question of building appropriate discrete representations from low-level sensorimotor values [135, 136, 137], some even going towards abstract symbolic representations [138, 139].”
• Bootstrapping bilinear models of Simple Vehicles (2015, background): “D(Y;X;U; ∆) is the set of all discrete-time dynamical systems with sampling interval ∆.”
• Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents (2010, background): “Basic definitions and notation will follow Sutton & Barto (1998). At every time step, the agent observes a state s , and selects an action a .”