search

inoryy / reaver

Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
MIT License
554 stars 89 forks source link

Rewards clipping or scaling #1

Closed inoryy closed 6 years ago

inoryy commented 6 years ago

Need to investigate if clipping or scaling rewards improves performance.

Does it even make sense if I'm already clipping grads?
How will the agent known that one action is better than other if both get reward = 1?

inoryy commented 6 years ago

Got an answer from DM - they don't use any reward clipping/scaling