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

Experiment 1: SARSA, α=0.1, γ=0.5, Greedy Exploit = 80%, and initial Q-value = 0: 1152181 Experiment 5: SARSA, α=0.1, γ=0.1, Greedy Exploit = 80%, and initial Q-value = 0: 225610 Compare the results of the first experiment to the fifth experiment. The first experiment should get a significantly higher reward than the fifth experiment. The γ parameter affects how much weight the future reward is given when updating the Q-value. When the weight is set too low (0.1 in experiment 5) this prevents the agent from taking into account a sequence of actions which could lead to a high reward.

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