A2C and VPG

[hades-rp2010]

Wrt #375 Mades some changes in discount.py (Really silly mistakes) Now the 2 agents are training

[codecov[bot]]

Codecov Report

Merging #383 into master will increase coverage by 0.00%. The diff coverage is 100.00%.

@@           Coverage Diff           @@
##           master     #383   +/-   ##
=======================================
  Coverage   91.28%   91.28%           
=======================================
  Files          90       90           
  Lines        3809     3810    +1     
=======================================
+ Hits         3477     3478    +1     
  Misses        332      332           

Impacted Files	Coverage Δ
genrl/agents/deep/a2c/a2c.py	93.58% <100.00%> (ø)
genrl/agents/deep/vpg/vpg.py	94.33% <100.00%> (ø)
genrl/utils/discount.py	100.00% <100.00%> (ø)