<--- Back to Details
First PageDocument Content
Arcade games / Reinforcement learning / Recurring enemies in the Mario series / Mario / Artificial intelligence / Partially observable Markov decision process / Action selection / Games / Digital media / Electronic games
Date: 2011-09-14 20:33:21
Arcade games
Reinforcement learning
Recurring enemies in the Mario series
Mario
Artificial intelligence
Partially observable Markov decision process
Action selection
Games
Digital media
Electronic games

Add to Reading List

Source URL: cs229.stanford.edu

Download Document from Source Website

File Size: 143,05 KB

Share Document on Facebook

Similar Documents

Assisting Persons with Dementia during Handwashing Using a Partially Observable Markov Decision Process Jesse Hoey1 , Axel von Bertoldi2 , Pascal Poupart3 , and Alex Mihailidis2 1

DocID: 1uKbd - View Document

Artificial intelligence / Robotics / Dynamic programming / Markov processes / Stochastic control / Machine learning / Probability theory / Probability / Partially observable Markov decision process / Humanoid robot / Reinforcement learning / Humanrobot interaction

Online Development of Assistive Robot Behaviors for Collaborative Manipulation and Human-Robot Teamwork Bradley Hayes and Brian Scassellati Yale University Computer Science Department New Haven, CT 06511

DocID: 1rp22 - View Document

Artificial intelligence / Systems science / Academia / International Conference on Autonomous Agents and Multiagent Systems / Reinforcement learning / International Joint Conference on Artificial Intelligence / Agent-based model / Partially observable Markov decision process / Multi-agent system / Intelligent agent / Peter Stone

IFAAMAS Board Elections 2016 Statement Bio Matthijs Spaan is an assistant professor of Computer Science at Delft University of Technology, the Netherlands. He holds a PhD degree in Computer Scienceand an MSc degr

DocID: 1riFB - View Document

Automated planning and scheduling / Hierarchical task network / Partially observable Markov decision process / Robotics / Robot / Windows Task Scheduler / Probability theory / Software / Computing

Social Hierarchical Learning: Enabling Human-Robot Teaming Bradley Hayes Dept. of Computer Science,Yale University Human-robot teaming has the potential to enable robots to perform well beyond

DocID: 1qGiF - View Document

Statistics / Statistical theory / Probability / Bayesian statistics / Dynamic programming / Markov processes / Stochastic control / Markov decision process / Reinforcement learning / Q-learning / Prior probability / Conjugate prior

Competing with Humans at Fantasy Football: Team Formation in Large Partially-Observable Domains

DocID: 1qBkM - View Document