Patrick MacAlpine
YOU?
Author Swipe
View article: Walking and falling: Using robot simulations to model the role of errors in infant walking
Walking and falling: Using robot simulations to model the role of errors in infant walking Open
What is the optimal penalty for errors in infant skill learning? Behavioral analyses indicate that errors are frequent but trivial as infants acquire foundational skills. In learning to walk, for example, falling is commonplace but appears…
View article: Design and Optimization of an Omnidirectional Humanoid Walk: A Winning Approach at the RoboCup 2011 3D Simulation Competition
Design and Optimization of an Omnidirectional Humanoid Walk: A Winning Approach at the RoboCup 2011 3D Simulation Competition Open
This paper presents the design and learning architecture for an omnidirectional walk used by a humanoid robot soccer agent acting in the RoboCup 3D simulation environment. The walk, which was originally designed for and tested on an actual…
View article: Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL
Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL Open
A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks …
View article: Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark Open
The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning. Generalization remains one of the most fundamental challe…
View article: Special issue on adaptive and learning agents 2019
Special issue on adaptive and learning agents 2019 Open
An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.
View article: Multi-Preference Actor Critic
Multi-Preference Actor Critic Open
Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide additi…
View article: Variety Wins: Soccer-Playing Robots and Infant Walking
Variety Wins: Soccer-Playing Robots and Infant Walking Open
Although both infancy and artificial intelligence (AI) researchers are interested in developing systems that produce adaptive, functional behavior, the two disciplines rarely capitalize on their complementary expertise. Here, we used socce…
View article: Multilayered skill learning and movement coordination for autonomous robotic agents
Multilayered skill learning and movement coordination for autonomous robotic agents Open
With advances in technology expanding the capabilities of robots, while at the same time making robots cheaper to manufacture, robots are rapidly becoming more prevalent in both industrial and domestic settings. An increase in the number o…