HumanCompatibleAI / adversarial-policies

Find best-response to a fixed policy in multi-agent RL
MIT License
275 stars 47 forks source link

Upgrade Stable Baselines #25

Closed AdamGleave closed 5 years ago

AdamGleave commented 5 years ago

The version of Stable Baselines we currently depend on defaults to installing TF 2, which is not supported. Update Stable Baselines to most recent version, which amongst other changes fixes this requirements issue.

Closes #24

codecov[bot] commented 5 years ago

Codecov Report

Merging #25 into master will decrease coverage by 0.02%. The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff            @@
##           master     #25      +/-   ##
=========================================
- Coverage   58.32%   58.3%   -0.03%     
=========================================
  Files          58      58              
  Lines        4914    4914              
=========================================
- Hits         2866    2865       -1     
- Misses       2048    2049       +1
Flag Coverage Δ
#aprl 10.8% <ø> (ø) :arrow_up:
#modelfree 51.36% <ø> (-0.03%) :arrow_down:
Impacted Files Coverage Δ
src/modelfree/visualize/annotated_gym_compete.py 83.03% <0%> (-0.61%) :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 5e4ddad...79338ab. Read the comment docs.