More comprehensive unit testing

[sampreet-arthi]

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.