An Application of Reinforcement Learning to Aerobatic Helicopter Flight

By Pieter Abbeel, Adam Coates, Morgan Quigley, Andrew Y. Ng. 2006

690 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Control and Systems Engineering, Reinforcement Learning, Robotics & Control

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

In Computational Theory and Mathematics

In Control and Systems Engineering

In Reinforcement Learning

In Robotics & Control

Citations in the corpus

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates (2016, methodology): “Reinforcement learning (RL) methods have been applied to range of robotic control tasks, from locomotion [1], [2] to manipulation [3], [4], [5], [6] and autonomous vehicle control [7].”
Model-based reinforcement learning with parametrized physical models and optimism-driven exploration (2015, background): “However, an interesting avenue for future work would be to combine our linear models with more expressive statistical models that can account for unmodeled effects, similar to prior work on autonomous vehicle control [2], [24].”
Designing Interpretable Approximations to Deep Reinforcement Learning with Soft Decision Trees (2020, methodology): “We use the methodology of imitation learning (Abbeel et al. 2007; Bain 1995) to train our simpler and more interpretable decision trees (students) to imitate the complex trained DQN (expert).”
Reinforcement learning in robotics: A survey (2013, background): “Control Abbeel et al. (2006); An et al.”
Deep Q-learning From Demonstrations (2017, neutral): “It still remains difficult to apply these algorithms to real world settings such as data centers, autonomous vehicles (Hester and Stone 2013), helicopters (Abbeel et al. 2007), or recommendation systems (Shani, Heckerman, and Brafman 2005).”
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image (2016, background): “Conventionally, learning-based approaches to autonomous flight have relied on learning from demonstration [2, 1, 30, 34].”
Deep visual foresight for planning robot motion (2016, background): “The high dimensionality of image observations presents a substantial challenge to model-based approaches, which have been most successful for low-dimensional non-visual tasks [21] such as helicopter control [22], locomotion [23], and robotic cutting [24].”
Multiagent Learning: Basics, Challenges, and Prospects (2012, background): “Some work has already successfully explored the integration of learning in these realworld domains and has shown promising results that justify a stronger focus by the community on complex systems; for example, see Richter, Aberdeen, and Yu (2006); Kalyanakrishnan, Liu, and Stone (2006); Abbeel et a”
Learning from Demonstrations for Real World Reinforcement Learning (2017, methodology): “It still remains difficult to apply these algorithms to real world settings such as data centers, autonomous vehicles Hester & Stone (2013), helicopters Abbeel et al. (2007), or recommendation systems Shani et al. (2005).”
Sim-to-Real Reinforcement Learning for Deformable Object Manipulation (2018, methodology): “has not yet been extensively applied to cloth manipulation, even though it has found applications in many other robotic domains, including rigid object manipulation [21, 22], UAV control [23] or bipedal robot control [24].”
Reinforcement learning with multi-fidelity simulators (2014, background): “We also describe the assumptions made about our multi-ﬁdelity simulators.”
Learning Dexterous Manipulation Policies from Experience and Imitation (2016, background): “Although robotic reinforcement learning has experienced considerable progress in recent years, with successful results in domains ranging from flight (Abbeel et al. 2006) to locomotion (Tedrake et al.”
Learning model-free robot control by a Monte Carlo EM algorithm (2009, background): “Reinforcement Learning (RL) is a notable paradigm for robot control with several reported successes in recent years (Tedrake et al., 2005; Abbeel et al., 2007; Kober and Peters, 2009; Riedmiller et al., 2009; Martinez-Cantin et al., 2009).”
Algorithms for Reinforcement Learning (2010, background): “…et al., 2009)), learning in robotics (e.g., controlling quadrupedales (Kohl and Stone, 2004), humanoid robots (Peters et al., 2003), or helicopters (Abbeel et al., 2007)), and applications to finance (e.g., option pricing (Tsitsiklis and Van Roy, 1999b, 2001; Yu and Bertsekas, 2007; Li et al.,…”
Manipulators and Manipulation in high dimensional spaces (2016, methodology): “Although robotic reinforcement learning has experienced considerable progress in recent years, with successful results in domains ranging from flight [3] to locomotion [101] to manipulation [81][103][80], comparatively few methods have been applied to control dexterous hands.”