Writing Stratagus-playing Agents in Concurrent ALisp

Stratagus has been used extensively in academia for AI research.
Post Reply
User avatar
Kyran
Posts: 499
Joined: Sat Dec 31, 2011 5:19 pm
Location: Australia
Contact:

Writing Stratagus-playing Agents in Concurrent ALisp

Post by Kyran »

We describe Concurrent ALisp, a language that allows the augmentation of reinforcement learning algorithms with prior knowledge about the structure of policies, and show by example how it can be used to write agents that learn to play a subdo-main of the computer game Stratagus.
Attachments
StratagusAgentsinConcurrentALisp.pdf
(216.31 KiB) Downloaded 870 times
04:27 jim4 why haven't you added wc1 support? this project sucks. i'm only going to use freecraft
05:06 jim4 finished wc1 support yet? i've been waiting for 6 years
05:10 jim4 new things scare me
User avatar
Big Daddy
Posts: 118
Joined: Sun Jan 08, 2012 11:23 pm

Re: Writing Stratagus-playing Agents in Concurrent ALisp

Post by Big Daddy »

8 Conclusion
We have outlined an approach to writing programs that play
games like Stratagus using partial programming with concurrent
ALisp, and demonstrated its effectiveness on a subdomain
that would be difficult for conventional reinforcement
learning methods. In the near future, we plan to implement
our improved learning algorithm, and scale up to increasingly
larger subgames within Stratagus.
According to http://citeseerx.ist.psu.edu/viewdoc/su ... 1.1.108.75, this article was written in 2005.
Who wants to bet they never followed through with their future plans?
User avatar
Kyran
Posts: 499
Joined: Sat Dec 31, 2011 5:19 pm
Location: Australia
Contact:

Re: Writing Stratagus-playing Agents in Concurrent ALisp

Post by Kyran »

They probably did in one of the other papers.
04:27 jim4 why haven't you added wc1 support? this project sucks. i'm only going to use freecraft
05:06 jim4 finished wc1 support yet? i've been waiting for 6 years
05:10 jim4 new things scare me
Post Reply