search

ai4co / rl4co

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)
https://rl4.co
MIT License
381 stars 70 forks source link

QOL improvements #185

Closed fedebotu closed 3 months ago

fedebotu commented 3 months ago

Description

A series of small but (imo) welcome improvements in quality of life (QOL) and misc

  1. Fix double printing of config when running Hydra
  2. Now the logged keys are smartly nested and can be searched in loggers such as Wandb
  3. Default depot_distribution to None. If so, the depot is sample from the loc_distribution

Types of changes

What types of changes does your code introduce? Remove all that do not apply: