Simulated Annealing Results

Estimated Return

These graphs show the estimated return for the final (equilibrium) policy at each temperature. The red line is the optimal policy.

Estimated Return for Run 4

Estimated Return for Run 5

Estimated Return for Run 6

Estimated Return for Run 7

Estimated Return for Run 8

Estimated Return for Run 9

Estimated Return for Run 10

Estimated Return for Run 11

Estimated Return for Run 12

Estimated Return for Run 13

Estimated Return for Run 14

Estimated Return for Run 15

States

These graphs show the number of states in the policy at each time step

States form Run 4

States form Run 5

States form Run 6

States form Run 7

States form Run 8

States form Run 9

States form Run 10

States form Run 11

States form Run 12

States form Run 13

States form Run 14

States form Run 15