search

AGI-Labs / continual_rl

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.
MIT License
105 stars 11 forks source link

Residual Configs Missing #12

Open SamNPowers opened 1 year ago

SamNPowers commented 1 year ago

This repo is missing the residual configs used in the CoLLAs paper.

Also TODO: make sure nothing else significant did not get ported.

(For my own reference: the commit has in the private repo corresponding to the experiments is: 'v1.0.0-141-g1601a230')