AISpace2 Main Tools News Downloads Prototype Tools Customizable Applets Practice Exercises Help About AIspace

Run an experiment for each of these parameter settings and record the total reward received. SARSA, α=0.1, γ=0.5, Greedy Exploit = 80%, and initial Q-value = 0: 1152181 Q-learning, α=0.1, γ=0.5, Greedy Exploit = 80%, and initial Q-value = 0: 641052 SARSA, α=0.1, γ=0.5, Greedy Exploit = 100%, and initial Q-value = 20: 2664318 Q-learning, α=0.1, γ=0.5, Greedy Exploit = 100%, and initial Q-value = 20: 2664659 SARSA, α=0.1, γ=0.1, Greedy Exploit = 80%, and initial Q-value = 0: 225610 SARSA, α=0.9, γ=0.5, Greedy Exploit = 80%, and initial Q-value = 0: 246605

Main Tools: Graph Searching | Consistency for CSP | SLS for CSP | Deduction | Belief and Decision Networks | Decision Trees | Neural Networks | STRIPS to CSP