Planning in Stochastic Environments with a Learned Model

Open paper
Benchmark Model Rank Results
2048-on-2048Stochastic Muzero#1Average Score: 500000
2048-on-2048AlphaZero (With Simulator)#2Average Score: 500000
2048-on-2048MuZero#3Average Score: 300000

Rank counts only results with a code link.