Article View: aus.computers.parallel
Article #200ACS NSW AI SIG Monthly meeting Wednesday 25th November 1998
From: Michael Williams
Date: Wed, 11 Nov 1998 00:00
Date: Wed, 11 Nov 1998 00:00
32 lines
1744 bytes
1744 bytes
ACS NSW AISIG - Artificial Intelligence - Monthly Meeting
Date: Wednesday 25th November 1998.
Time: 6:30pm till 8:00pm & dinner afterwards.
Topic: Reinforcement learning is the problem faced by an agent that
learns behaviour through trial and error interactions with a
dynamic environment. It dates back to Arthur Samuel's famous
checkers program and has recently captured the AI community's
interest with Gerry Tesauro's TD-Gammon program, which has
learnt to play backgammon better than any other computer program
and almost as well as the best humans. This talk is an overview
and introduction to RL with some examples and discussion on open
problems.
Speaker: Bernhard Hengst
Place: ACS NSW Offices, 3rd floor, PSA House
160 Clarence Street, Sydney
between Market & King Streets, closer to Town Hall than Wynyard
Contact: Michael Williams (02)9744-4759
michaelw@acslink.net.au
--
To reply first remove 'xspam' from the address.
Technical Details
Message-ID:
<01be0d4e$9c0165a0$f030c018@mikes-pc.c2.telstra-mm.net.au>Path:
arc1-ca.pugleaf.net!unknown!not-for-mailShow Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: f9e8f,3820ca128241e45c,start X-Google-Attributes: gidf9e8f,public From: "Michael Williams" <mwilliam@nsw.xspam.bigpond.net.au> Subject: ACS NSW AI SIG Monthly meeting Wednesday 25th November 1998 Date: 1998/11/11 Message-ID: <01be0d4e$9c0165a0$f030c018@mikes-pc.c2.telstra-mm.net.au> X-Deja-AN: 410626842 X-Complaints-To: news@m2.c2.telstra-mm.net.au X-Trace: m2.c2.telstra-mm.net.au 910773456 20612 24.192.48.240 (11 Nov 1998 08:37:36 GMT) Organization: Telstra Big Pond Cable - Sydney Site 1 Reply-To: "Michael Williams" <michaelw@xspam.acslink.net.au> NNTP-Posting-Date: 11 Nov 1998 08:37:36 GMT Newsgroups: aus.computers.parallel