rlworkgroup / garage

A toolkit for reproducible reinforcement learning research.
MIT License
1.88k stars 310 forks source link

Make plotting plot the learner in BC #2127

Closed krzentner closed 4 years ago

krzentner commented 4 years ago

Before, using BC with an expert source policy caused the expert to be shown in the plotter, which was very confusing. This change fixes that, by making the expert the algorithm's .exploration_policy and the learner its .policy

codecov[bot] commented 4 years ago

Codecov Report

Merging #2127 into master will decrease coverage by 0.01%. The diff coverage is 100.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master    #2127      +/-   ##
==========================================
- Coverage   93.16%   93.14%   -0.02%     
==========================================
  Files         194      194              
  Lines       10523    10525       +2     
  Branches     1323     1323              
==========================================
  Hits         9804     9804              
- Misses        473      476       +3     
+ Partials      246      245       -1     
Impacted Files Coverage Δ
src/garage/torch/algos/bc.py 92.10% <100.00%> (+0.21%) :arrow_up:
src/garage/sampler/multiprocessing_sampler.py 89.61% <0.00%> (-1.30%) :arrow_down:

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 83ba45c...4491cd6. Read the comment docs.

krzentner commented 4 years ago

@Mergifyio rebase

mergify[bot] commented 4 years ago

Command rebase: success

Branch has been successfully rebased

krzentner commented 4 years ago

@mergifyio rebase

mergify[bot] commented 4 years ago

Command rebase: success

Branch has been successfully rebased