[Final experiments - REINFORCE] experiment #2 with seed 1000

[ziritrion]

Final experiment with our REINFORCE algorithm implementation. showing a final reward of 329.5 with a preset seed of value 1000.

The Learning Rate hyperparameter for REINFORCE was 1*10^-5, since this was the value that showed best results for training in our experiments.

The action set chosen for all experiments is the following:
[0.0, 0.3, 0.0], # throttle
[0.0, 0.1, 0.0], # throttle
[0.0, 0.0, 0.0], # throttle
[0.0, 0.0, 0.7], # break
[0.0, 0.0, 0.5], # break
[0.0, 0.0, 0.2], # break
[-1.0, 0.0, 0.05], # left
[-0.5, 0.0, 0.05], # left
[-0.2, 0.0, 0.05], # left
[1.0, 0.0, 0.05], # right
[0.5, 0.0, 0.05], # right
[0.2, 0.0, 0.05], # right

TensorBoard screenshots below:

Generated video below:
https://user-images.githubusercontent.com/1465235/114518058-4043f400-9c3f-11eb-994b-701b443604dd.mp4