[Lisa_teatalk] Fwd: Damien Ernst talk, ***Wed October 8***, 2pm, MC 437

Yoshua Bengio yoshua.bengio at gmail.com
Fri Oct 3 16:30:22 EDT 2014


---------- Forwarded message ----------
From: Doina Precup <dprecup at cs.mcgill.ca>
Date: Fri, Oct 3, 2014 at 2:14 PM
Subject: Damien Ernst talk, ***Wed October 8***, 2pm, MC 437
To: "labrl at cs.mcgill.ca" <labrl at cs.mcgill.ca>, Bengio Yoshua <
bengioy at iro.umontreal.ca>
Cc: "dernst at ulg.ac.be" <dernst at ulg.ac.be>


Hi everyone,

Damien Ernst (http://www.montefiore.ulg.ac.be/~ernst/) will be visiting us
the coming Wed. He will give a talk at 2pm in MC 437, titled:

Batch Mode Reinforcement Learning based on the Synthesis of Artificial
Trajectories

Abstract:
We consider the batch mode reinforcement learning setting, where the
central problem is to learn from a sample of trajectories a policy that
satisfies or optimizes a performance criterion. We focus on the continuous
state space case for which usual resolution schemes rely on function
approximators either to represent the underlying control problem or to
represent its value function. As an alternative to the use of function
approximators, we rely on the synthesis of “artificial trajectories” from
the given sample of trajectories, and show that this idea opens new avenues
for designing and analyzing algorithms for batch mode reinforcement
learning.

Best,
Doina
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20141003/a793aa9d/attachment.html 


More information about the Lisa_teatalk mailing list