Common usage of running the demo programs is described here.

 

Build the Demo Program

Execute:

 $ cd benchmarks/DEMO_DIR
 $ make

Here, DEMO_DIR is each demo directory. See Documentation/Installation Guide for the detail.

Running Command

Execute as follows:

 $ ./DEMO_PRG -path PATH_LIST -agent AGENT_FILE -outdir OUT_DIR

Here, the demo-specific elements are:

DEMO_PRG
Demo program whose name is *.out.
PATH_LIST
Comma separated path list for the demo program to search agent scripts.
AGENT_FILE
Comma separated agent script(s) in which a reinforcement learning module and the other modules are configured.
OUT_DIR
Result directory into which the program store some data. You need to create OUT_DIR before running; if non-existet directory is specified, no result is stored.

Result Analysis

In OUT_DIR, the following files are stored:

cmdline
Command line of the execution.
before.agent, after.agent
A whole agent script generated by the program (before the execution and after the execution, respectively).
ext_sto
External storage directory (maybe not used in this case).
included
Directory to store the copy of every included agent file.
log-eps-ret.dat
Log file of (episode number, return in the episode).
log-action-res.dat
Log file of each action.

For example, use gnuplot to plot the learning curve as:

 $ gnuplot
 gnuplot> plot 'log-eps-ret.dat' w l
rl1-eps-ret.png

Miscellaneous

In order to specify the random seed, just append an agent file as follows:

 $ ./maze2d.out -path ../cmn,m -agent ql_da1,seed0 -outdir result/rl1

This is a case of the Maze2D task. Here, seed0 is m/seed0.agent; in this file, the random seed is set to be zero. By specifying the random seed, we can obtain the same result in every run.

 

 



Attach file: filerl1-eps-ret.png 1091 download [Information]

Front page   Edit Freeze Diff Backup Upload Copy Rename Reload   New List of pages Search Recent changes   Help   RSS of recent changes
Last-modified: 2011-05-26 (Thu) 06:58:30 (3100d)