Imitation and Reinforcement Learning

By Jens Kober, Jan Peters. 2010

152 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, 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. Sergey Levine
2. Chelsea Finn
3. Li Fei-Fei
4. Pieter Abbeel
5. Silvio Savarese
6. Jan Peters
7. Yuke Zhu
8. George Dimitri Konidaris

In Control and Systems Engineering

1. Jan Peters
2. Sergey Levine
3. Yuke Zhu
4. Li Fei-Fei
5. Silvio Savarese
6. Ajay Mandlekar
7. Marc Peter Deisenroth
8. George Dimitri Konidaris

In Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. George Dimitri Konidaris
4. Jan Peters
5. Ofir Nachum
6. Chelsea Finn
7. Silvio Savarese
8. Gerhard Neumann

Citations in the corpus

• Learning Parameterized Skills (2012, methodology): “We use PoWER due to its simplicity and because it has been empirically shown to outperform other policy learning algorithms in a variety of standard benchmarks and on real robotics problems [32].”
• Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations (2020, background): “Imitation learning has been applied to multiple domains such as playing table tennis [22], Go [37] and video games [33], and driving autonomously [4, 31] In robotics, the idea of robots learning from human demonstrations have been extensively explored [36, 17, 23, 11, 14, 3, 5].”
• Provable Representation Learning for Imitation with Contrastive Fourier Features (2021, background): “, in health [18] and robotics [24] applications.”
• Imitation Learning (2017, methodology): “Using damping in dynamic systems is a common approach when combining imitation learning and reinforcement learning [Kober and Peters 2010; Kober et al. 2013].”
• Probabilistic model-based imitation learning (2013, methodology): “RL has been successfully used in robotics applications for learning the ball-in-a-cup game [19] and helicopter hovering [28].”
• Model-based imitation learning by probabilistic trajectory matching (2013, background): “a robot learn the ball-in-a-cup game, where the learning was initialized by human demonstrations [14].”
• A survey of inverse reinforcement learning techniques (2012, methodology): “The major difficulty is to combine these MPs into full movements and some practical methods have been developed (Kober and Peters, 2010).”
• HG-DAgger: Interactive Imitation Learning with Human Experts (2018, methodology): “Data is gathered from an expert policy and is used to train a novice policy [1], [2].”
• MimicPlay: Long-Horizon Imitation Learning by Watching Human Play (2023, methodology): “Imitation Learning (IL) has enabled robots to successfully perform various manipulation tasks [1, 4, 9, 14, 15, 22, 26, 40].”
• An Artificial Agent for Robust Image Registration (2016, background): “Guided policy search (Levine and Koltun 2013) and imitation learning (Kober and Peters 2010) were proposed for more efficient RL via improved policy/data sampling, which however are not directly applicable to the end-to-end trainable DRL framework.”
• DropoutDAgger: A Bayesian Approach to Safe Imitation Learning (2017, background): “Recently, there have been many advances in robotics driven by breakthroughs in deep imitation learning [1], [2].”