I am looking to find standard reinforcement learning implementations in C, C++ or Python, to be able to adapt to my problem which is compiler optimizations.
Looking at the link attached bellow it seems all the C++ implementations are bad linked. Anyone has any suggestions?
http://www-anw.cs.umass.edu/rlr/domains.html
Dear Amir H. Ashouri,
You may get details of a PhD work related to this topic. Hope that may help you. With best wishes, Good Luck.
http://www.cs.cmu.edu/~sross1/cv.pdf
Hi. Please find here a list of various packages I found 2 years ago: https://sites.google.com/site/alexsusu/rl_and_mdp_pointers . Let me know if you find anything else interesting.
Dear Amir H. Ashouri,
You may get details of a PhD work related to this topic. Hope that may help you. With best wishes, Good Luck.
http://www.cs.cmu.edu/~sross1/cv.pdf
HI. You can take a look at http://deeplearning.net
They support a python module called theano (http://deeplearning.net/software/theano/) that allows a "transparent use of a GPU" and other optimizations.
"Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Theano features:
- tight integration with NumPy – Use numpy.ndarray in Theano-compiled functions.
- transparent use of a GPU – Perform data-intensive calculations up to 140x faster than with CPU.(float32 only)
- efficient symbolic differentiation – Theano does your derivatives for function with one or many inputs.
- speed and stability optimizations – Get the right answer for log(1+x) even when x is really tiny.
- dynamic C code generation – Evaluate expressions faster.
- extensive unit-testing and self-verification – Detect and diagnose many types of mistake."
Thanks @Ramon, but I would like to use R-L not the deep-learning and the area is compiler optimization, not Heterogeneous compilation for CPU/GPU
Mr. Ahmad and Mr. Perez have sugguested graduate level websites for interactive and responsive learning. Just to be consistent and complete, have you tried the very common www.W3schools.com for small code reduction examples?
John Wilson
Stratford University
@John, could yo elaborate on that? Not quite sure if I am understood.
Hi, I am not aware of any complete implementation. If you are dealing with discrete states and action spaces, you can build one yourself. For my work in RL I started from the partial implementation provided from Univ. of Berkeley to his AI students (http://ai.berkeley.edu/reinforcement.html) and filled the missing classes. With this package, you get a Pacman environment, which is nice for testing purposes.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python