Does the move_reward_weight is the annealing factor in the formula 1 in the paper?

openai / multiagent-competition

Code for the paper "Emergent Complexity via Multi-agent Competition"

https://arxiv.org/abs/1710.03748

806 stars 153 forks source link

Does the move_reward_weight is the annealing factor in the formula 1 in the paper? #3

Closed Kelvinson closed 5 years ago

Kelvinson commented 6 years ago

Hi,

I want to implement the training process of the multiagent-competition, I am wondering whether move_reward_weight is the annealing factor in the formula 1 in the paper and how can I make it anneal to 0 in the specified timestamps during the training, thank you!