Using dimensionality reduction to exploit constraints in reinforcement learning
By Sebastian Bitzer, Matthew J. Howard, Sethu Vijayakumar. 2010
55 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Biomedical Engineering
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
- Sergey Levine
- Pieter Abbeel
- Percy Liang
- Jan Peters
- Chelsea Finn
- Mohit Bansal
- Jianfeng Gao
- Quoc V. Le
In Biomedical Engineering
- Jan Peters
- Jens Kober
- Oliver Kroemer
- J. Bagnell
- Katharina Muelling
- Percy Liang
- Andrea Lockerd Thomaz
- Gerhard Neumann
Citations in the corpus
- Reinforcement learning in robotics: A survey (2013, methodology): “This method has resulted in applications including T-ball batting (Peters and Schaal, 2008c,b), reaching tasks (Guenter et al., 2007; Bitzer et al., 2010), ball-in-a-cup (Kober and Peters, 2009), flipping a light switch (Buchli et al.”
- Keyframe-based Learning from Demonstration (2012, unknown): “A recent approach is to only record keyframes and use them to learn a constraint manifold for the state space in a reinforcement learning setting [7].”
- Novel Interaction Strategies for Learning from Teleoperation (2012, background): “A recent approach is to record keyframes and use them to learn a constraint manifold for the state space in a reinforcement learning setting (Bitzer, Howard, and Vijayakumar 2010).”
- Learning to select and generalize striking movements in robot table tennis (2012, methodology): “Here, learning from demonstrations can provide a good starting point for motor skill learning as it allows the efficient acquisition of single movement primitives (Guenter et al., 2007; Peters and Schaal, 2008b; Kober et al., 2008; Peters and Schaal, 2008a; Bitzer et al., 2010).”
- Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration (2018, background): “At the same time, simple strategies to combat overfitting (e.g. using fewer parameters or regularization) cripple the policy’s flexibility (Bitzer et al., 2010), which is required for complex spatial and structural reasoning in user interfaces.”
- Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective (2012, background): “We find that both are suitable to kinesthetic teaching from the user’s perspective and both communicate different information.”