Pierre-Luc Bacon's repositories
lagrangian-rl
Experiments for the paper A Lagrangian Method for Inverse Problems in Reinforcement Learning.
timedaction
Asynchronous timer notification using timerfd and epoll
skill-acquisition
Automatic construction of temporally extended actions within the options framework
vfpolytope
Reproduction of figure 2 d) from Dadashi et al. (2019)
jabber-rpc
Jabber-RPC implementation based on Smack. A fork of xmppxmlrpcapi from Ulrich Staudinger.
option_critic
Implementation of the Option-Critic Architecture on the Atari (ALE) environment
ai-deadlines
:alarm_clock: AI conference deadline countdowns
Arcade-Learning-Environment
The Arcade Learning Environment (ALE) -- a platform for AI research.
awesome-cs-conferences
A list of top-ranked computer science conference submission deadlines
flask-zotero
Example app using Flask-oauth to connect and retrieve items from Zotero
guerilla-cluster
A set of bash tools for distributed computing on a "guerilla cluster" (an improvised aggregate of disparate computers)
linear_options
State and temporal abstraction for SMDP in continuous state spaces using linear options
pendulum_tracking
Color tracking using a Kalman filter and pendulum model
pierrelux.github.com
pierrelux.github.com