Improving Policies via Search in Cooperative Partially Observable Games — mentioned by 3PS

Fri, 11 Sep 2020 17:23:22 GMT

Recently there has been a growing interest in developing AI for cooperative games, like Hanabi. I believe the challenge originated from a paper by Google Brain/DeepMind [1], but several other groups have tackled it, including Facebook AI Research [2]. [1] https://www.sciencedirect.com/science/article/pii/S000437021... [2] https://arxiv.org/pdf/1912.02318v1.pdf

Paper and discussion history. A mention is not an endorsement.

Improving Policies via Search in Cooperative Partially Observable Games — mentioned by gwenzek

Sat, 18 Jul 2020 21:34:04 GMT

Hanabi has been solved a few months after deepmind "new frontier" paper: https://arxiv.org/abs/1912.02318 They reach a score of 24.6/25. Knowing that there are some losing hands.

Paper and discussion history. A mention is not an endorsement.

Improving Policies via Search in Cooperative Partially Observable Games · HackerPapers discussions

Improving Policies via Search in Cooperative Partially Observable Games — mentioned by 3PS

Improving Policies via Search in Cooperative Partially Observable Games — mentioned by gwenzek