Closed Kaixhin closed 8 years ago
As described in Generalization in Reinforcement Learning: Safely Approximating the Value Function. Will allow step in x and step in y of length 0.05 max each, with a cost of 10 per length unit travelled?
As described in Generalization in Reinforcement Learning: Safely Approximating the Value Function. Will allow step in x and step in y of length 0.05 max each, with a cost of 10 per length unit travelled?