2 problems
- 0 votes0 replies0 views
Removal of repeated training under degree preknowledge
Algorithmic simplification conjecture. If one has prior knowledge of the degree of or , the repeated-training and averaging step in Algorithm can be removed, because gen…
- 0 votes0 replies0 views
Conjecture on the convergence time of continuous-action reinforcement learning
Convergence-time conjecture. The convergence time, when the algorithm converges, is very high even for a quadratic cost function.