search

SforAiDl / genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
https://genrl.readthedocs.io
MIT License
403 stars 59 forks source link

Change numpy array to tensor in vpg.py #319

Closed Devanshu24 closed 4 years ago

Devanshu24 commented 4 years ago

The actual function (compute_returns_and_advantage) expects a torch.tensor but was being passed a numpy.ndarray Fixes #316

codecov[bot] commented 4 years ago

Codecov Report

Merging #319 into master will decrease coverage by 0.02%. The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #319      +/-   ##
==========================================
- Coverage   90.90%   90.87%   -0.03%     
==========================================
  Files          88       88              
  Lines        3705     3705              
==========================================
- Hits         3368     3367       -1     
- Misses        337      338       +1
Impacted Files Coverage Δ
genrl/agents/deep/vpg/vpg.py 94.33% <100.00%> (ø)
genrl/agents/classical/sarsa/sarsa.py 96.15% <0.00%> (-3.85%) :arrow_down:
Devanshu24 commented 4 years ago

What happened?

Sharad24 commented 4 years ago

Ouh. Closed it by mistake. Sorry

Devanshu24 commented 4 years ago

Ouh. Closed it by mistake. Sorry

Oh ok :D