Making Reinforcement Learning Work on Real Robots
By William D. Smart. 2002
109 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Sergey Levine
- Abhinav Kumar Gupta
- Pieter Abbeel
- Jitendra Malik
- Chelsea Finn
- Yoshua Bengio
- Trevor Darrell
- Lerrel Pinto
Citations in the corpus
- Visual Imitation Made Easy (2020, methodology): “ace. This method has been successfully applied to a large range of robotic tasks including flying a robotic helicopter [17], grasping objects [18, 19], navigating robots through cluttered environments [20, 21, 22], and even driving cars [23]. Teleoperation has been successful in solving a wide variet”
- Application on Reinforcement Learning for Diagnosis Based on Medical Image (2008, methodology): “For example, a reinforcement learning algorithm has performed the medical diagnosis (Stensmo & Sejnowski, 1996), bioinformatics (Sahba et al, 2006), speech recognition (Rabiner, 1989), spell recognition (Raedt & Bruynooghe, 2004), computational vision and even robots locomotion ( Smart, 2002 ).”
- Effective reinforcement learning for mobile robots (2002, methodology): “Otherwise,thepredictionusingLWRisreturned. Thisalgorithmhasbeenshowntolearnfaster thanonebasedonlyonLWA,andtoberobustacross a number of test domains [ 6 ].”
- Interactive Policy Learning through Confidence-Based Autonomy (2014, methodology): “ to autonomous systems. Compared to exploration-based methods, demonstration learning often reduces the learning time and eliminates the frequently difficult task of defining a detailed reward function (Smart, 2002; Schaal, 1997). In this article, we present an interactive demonstration learning algori”
- Experience Replay for Real-Time Reinforcement Learning Control (2012, methodology): “We also use easy missions [28] to speed up learning.”
- A survey of robot learning from demonstration (2009, unknown): “Demonstrations recorded through human teleoperation via a joystick are used in a variety of applications, including flying a robotic helicopter [6], robot kickingmotions [7], object grasping [8, 9], robotic arm assembly tasks [10] and obstacle avoidance and navigation [11,12].”