Giters

SforAiDl / genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL

Home Page:https://genrl.readthedocs.io

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

More comprehensive unit testing

sampreet-arthi opened this issue · comments

commented

There seem to be some vulnerabilities in our code that might fail easily. I suggest adding more unit tests for the following:

  • Custom agents (there's only VPG and PPO on CartPole-v0 as of now. We should preferably add more to cover discrete-offpolicy, continuous-offpolicy and continuous-onpolicy)
  • Evaluation for the Bandits and Classical agents
  • Testing of convergence of agents as proposed in #312
  • Buffers
  • VecEnv (no test for parallel vec envs)
  • Unit tests for all the ongoing projects (Model-based, Distributed, Offline, Evolutionary and MARL)

Not a priority at the moment but will have to do before the next release.