search

JuliaPOMDP / TabularTDLearning.jl

Julia implementations of temporal difference Reinforcement Learning algorithms like Q-Learning and SARSA
Other
10 stars 6 forks source link

POMDPs v0.8 Compatibility #7

Closed MaximeBouton closed 4 years ago

MaximeBouton commented 5 years ago

Do not merge yet. This package needs a bit more care:

This solver uses the mdp in its constructor, the exploration policy parameter should be re designed

codecov[bot] commented 4 years ago

Codecov Report

Merging #7 into master will decrease coverage by 1.83%. The diff coverage is 93.84%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master       #7      +/-   ##
==========================================
- Coverage   98.41%   96.58%   -1.84%     
==========================================
  Files           3        4       +1     
  Lines          63      117      +54     
==========================================
+ Hits           62      113      +51     
- Misses          1        4       +3
Impacted Files Coverage Δ
src/TabularTDLearning.jl 100% <ø> (ø)
src/sarsa_lambda.jl 95.55% <91.66%> (-4.45%) :arrow_down:
src/q_learn.jl 97.05% <95%> (+1.6%) :arrow_up:
src/sarsa.jl 97.29% <95.23%> (-2.71%) :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 11b2fc5...0aa87cd. Read the comment docs.