Fig. 4: DR-FREE and MaxDiff.
From: Distributionally robust free energy principle for decision-making
a MaxDiff success rates for different values of the sampling size and planning horizon. Experiments highlight a sweetspot in the hyperparameters with 100% success rate. Worst rates are obtained for low horizons, where the success rate is between 25% and approximately 40%. All experiments are performed with the temperature-like hyperparameter α set to 0.1. Data for each cells obtained from 12 experiments corresponding to the initial conditions in Fig. 3c. b Success rates for different values of α and samples when horizon is set to 2. Success rates are consistent with the previous panel—for the best combination of parameters, MaxDiff agent completes the task half of the times. See Supplementary Fig. 7 for a complementary set of MaxDiff experiments. c Robot trajectories using the MaxDiff policy when the horizon is equal to 2 and samples is set to 50. MaxDiff fulfills the task when the shortest path is obstacle-free. d DR-FREE allows the robot to complete the task when it is equipped with a generative model from MaxDiff computed using the same set of hyperparameters from the previous panel. e This desirable behavior is confirmed even when samples is decreased to 10. See “Methods” and Supplementary Information for details.
