Spinning Up附带了一个用于解释结果的简单绘图工具。 使用以下命令运行它：
python -m spinup.run plot [path/to/output_directory ...] [--legend [LEGEND ...]] [--xaxis XAXIS] [--value [VALUE ...]] [--count] [--smooth S] [--select [SEL ...]] [--exclude [EXC ...]]
strings. As many log directories (or prefixes to log directories, which the plotter will autocomplete internally) as you’d like to plot from. Logdirs will be searched recursively for experiment outputs.
The internal autocompleting is really handy! Suppose you have run several experiments, with the aim of comparing performance between different algorithms, resulting in a log directory structure of:
data/ bench_algo1/ bench_algo1-seed0/ bench_algo1-seed10/ bench_algo2/ bench_algo2-seed0/ bench_algo2-seed10/
You can easily produce a graph comparing algo1 and algo2 with:
python spinup/utils/plot.py data/bench_algo
relying on the autocomplete to find both
strings. Optional way to specify legend for the plot. The plotter legend will automatically use the
config.jsonfile, unless you tell it otherwise through this flag. This only works if you provide a name for each directory that will get plotted. (Note: this may not be the same as the number of logdir args you provide! Recall that the plotter looks for autocompletes of the logdir args: there may be more than one match for a given logdir prefix, and you will need to provide a legend string for each one of those matches—unless you have removed some of them as candidates via selection or exclusion rules (below).)
string. Pick what column from data is used for the x-axis.
strings. Pick what columns from data to graph on the y-axis. Submitting multiple values will produce multiple graphs. Defaults to
Performance, which is not an actual output of any algorithm. Instead,
Performancerefers to either
AverageEpRet, the correct performance measure for the on-policy algorithms, or
AverageTestEpRet, the correct performance measure for the off-policy algorithms. The plotter will automatically figure out which of
AverageTestEpRetto report for each separate logdir.
Optional flag. By default, the plotter shows y-values which are averaged across all results that share an
exp_name, which is typically a set of identical experiments that only vary in random seed. But if you’d like to see all of those curves separately, use the
int. Smooth data by averaging it over a fixed window. This parameter says how wide the averaging window will be.
strings. Optional selection rule: the plotter will only show curves from logdirs that contain all of these substrings.
strings. Optional exclusion rule: plotter will only show curves from logdirs that do not contain these substrings.