HumanCompatibleAI / adversarial-policies

Find best-response to a fixed policy in multi-agent RL
MIT License
275 stars 47 forks source link

`modelfree.utils.sacred_copy` no longer necessary #20

Open shwang opened 5 years ago

shwang commented 5 years ago

https://github.com/HumanCompatibleAI/adversarial-policies/blob/3a273ea9b7a02c34f95917bb56c1473e9a1af3eb/src/modelfree/common/utils.py#L44

https://github.com/IDSIA/sacred/issues/498 was resolved.

AdamGleave commented 5 years ago

The bug is still present in 0.7.5, I think we need to wait for Sacred 0.7.6 to come out.

AdamGleave commented 4 years ago

Although Sacred 0.8.x is now out, unfortunately we still need this because of https://github.com/IDSIA/sacred/issues/499