v0.2.0

Search Methods, Flexible Embeddings, New Graph Encoders and more 🚀

Search methods

• New flexible and extensible abstract class
• Active Search (Bello et al, 2016)
• Efficient Active Search (Hottung et al, 2022)

Flexible embeddings

• Support for changing any environment embedding (init, context and dynamic)
• Add new notebook showcasing how to solve new complex problems (example of multi-depot multi-agent pickup and delivery problem - MDPDP)

Support for torch-geometric

• Added new template graph neural networks (MPNN, GCN)
• Example Notebook here

Miscellaneous

• Separate loggers
• Better imports
• Bugfix compatibility with Mac
• Update configs
• ... and more!

v0.1.1

Better training, Bug fixes, and more 🚀

• Better automatic training with DDP #87
• Bug Fix RL4COTrainer
• Avoid broadcasting error warning in critic baselines
• Fix rollout baseline bug
• New experiment config structure: interpolate with environment name (we won't need anymore to have separate folders for each environment name such as TSP, CVRP etc, simply use one config to rule them all!

v0.1.0

Major release: refactoring of models, trainer and pipelines, and more! 🚀

• Refactored the old task class into a base class (RL4COLitModule) that is the base for RL algorithms (such as REINFORCE and PPO), following the discussion in #67
• New base class for construction methods: now encoder, decoder, policy, and model can be based on common parent classes to make implementation much more modular
• Added native loading from the checkpoint, which used to be buggy
• Nice new logo (we like it, but we are obviously biased, so feel free to give us your opinion ;) )
• Added mPDP environment (and added some WIP for EquityTransformer)
• New RL4COTrainer that automatically includes training tricks for RL
• Added Codecov coverage
• Better testing: now we thoroughly test most of the library, including training (the Hydra part as well!)
• Documentation overhaul: add Sphinx plugins for modularized, automatic docs
• ... and more!

v0.0.6

Better handling of notebooks, refactoring, plots and more!

Changelog of this release:

• Add notebook with checkpointing, logging, testing and more and relative bugfixes + feats #83
• Refactor env embeddings into init, context and dynamic
• OP plotting
• PCTSP plotting
• Quickfix Lightning problem: Lightning-AI/pytorch-lightning#18022
• Quickfix docs
• Misc

Full Changelog: v0.0.5...v0.0.6

v0.0.5

Changelog

• Fix SDVRP dynamic embedding #82
• Add missing environments in testing
• Update quickstart notebook to be more informative
• Remove rendering titles to avoid cluttering
• Other minor misc. updates

v0.0.4

Documentation, environment refactoring, SPCTSP and more!

• Add initial documentation on ReadTheDocs #80
• Major refactoring of environments: new subclasses (get_action_mask, check_solution_validity) and more modular operations such as get_tour_length, move the base class and utils under common/
• New SPCTSP environment
• Fix SDVRP, refactor as subclass of CVRP
• Fix OP with major refactoring; typos @eltociear
• Add Slack chat links
• Add paper link and citation
• Move dev status to Beta (it was production stable - we wish it was! Perhaps in the future... 🤞🏼)
• Misc bug fixes

v0.0.3

Bug Fixes and more!

Changelog:

• Solve #71 (pip install from PyPI now works!)
• Fix TSP rendering
• Add pre-commit-config (we will make a contribution guide in the near future)
• Linting action with Black+Ruff combo - handled by default by the pre-commit
• Add working Colab notebook with full training and testing of AM
• Add badges
• Misc

v0.0.2

NOTE: please do not use this version, as it only contains the __init__.py file