Presentation Schedule
Note: no more than three students should sign up for the same day.
Please send me your paper for approval one week before your
scheduled presentation date.
- Mar 20
- Mar 22: Hung Le, Playing FPS Games with Deep Reinforcement Learning; Javier Lores, A Neuroevolution
Approach to General Atari Gameplay; Saurabh Farkya,
Learning Visual Predictive Models of Physics for Playing Billiards
- Office Hours: Reema Shababou
- Mar 27: no class
- Mar 29: no class
- Apr 3: Mengmeng Chen, Linear Feature Encoding for Reinforcement Learning; Girish Kannan, Multi-robot Auctions for
Allocations of Tasks with Temporal Constraints; Nisarg Chitaliya, What Would You Do? Acting By Learning How to Predict
- Apr 5: Deepa Lakshmi, Robot path planning in uncertain environments
using multi-objective particle optimization; Reamonn Norat, Estimation
of player's preference for cooperative RPGs using multi-strategy Monte
Carlo method; Sayyed Jaffar Ali Raza, Efficient Path Planning Methods
for UAVs Inspecting Power Lines
- Apr 10: Saif Mohammed, Scale-aware navigation of a low-cost quadcopter
with a monocular camera; Brandon Jones, Towards automatic StarCraft
strategy generation using genetic programming; Nitish Gupta, An MCMC-based Particle Filter for Tracking Multiple Interacting Targets
- Apr 12: Jack Vice, Learning Genetic Representations for Classes of Real-valued Optimization Problems; Siavash Khodadedeh, Portfolio Greedy Search and Simulation for Large-scale Combat
in Starcraft; Sharare Zehtabian, Grounded Action Transformation for Robot Learning in Simulation
- Apr 17: no class
- Apr 19: Jose Sanchez; Nabil Ettehadi, A task parameterized probabilistic
model with minimal intervention control; Sahar Tavakoli, Mobile robot path planning using artificial bee colony and evolutionary programming