search

rlberry-py / rlberry

An easy-to-use reinforcement learning library for research and education.
https://rlberry-py.github.io/rlberry
MIT License
162 stars 30 forks source link

Little break #182

Closed riccardodv closed 2 years ago

riccardodv commented 2 years ago

https://github.com/rlberry-py/rlberry/blob/014fcd38b13d09abd61ed55ea6bbd357c25a33d7/rlberry/agents/torch/a2c/a2c.py#L226-L227

shouldn't we break? Like it is done some lines above in:

https://github.com/rlberry-py/rlberry/blob/014fcd38b13d09abd61ed55ea6bbd357c25a33d7/rlberry/agents/torch/a2c/a2c.py#L221-L222

riccardodv commented 2 years ago

https://github.com/rlberry-py/rlberry/blob/014fcd38b13d09abd61ed55ea6bbd357c25a33d7/rlberry/agents/torch/a2c/a2c.py#L254-L256

Why do we normalize rewards in A2C?