Fix for the infinite loop in Off Policy Agent tests

[sampreet-arthi]

trafficstars

[codecov[bot]]

Codecov Report

Merging #384 into master will decrease coverage by 0.15%. The diff coverage is 88.88%.

@@            Coverage Diff             @@
##           master     #384      +/-   ##
==========================================
- Coverage   91.28%   91.12%   -0.16%     
==========================================
  Files          90       90              
  Lines        3809     3809              
==========================================
- Hits         3477     3471       -6     
- Misses        332      338       +6     

Impacted Files	Coverage Δ
genrl/trainers/offpolicy.py	92.42% <87.50%> (ø)
genrl/agents/__init__.py	100.00% <100.00%> (ø)
genrl/agents/deep/td3/td3.py	87.93% <0.00%> (-5.18%)	:arrow_down:
genrl/agents/deep/sac/sac.py	90.00% <0.00%> (-3.34%)	:arrow_down: