Abstract | ||
---|---|---|
This paper considers the application of reinforcement learning to path finding tasks in continuous state space in the presence of obstacles. We show that cumulative evaluation functions (as Q-Functions [28] and V-Functions [4]) may be discontinuous if forbidden regions (as implied by obstacles) exist in state space. As the infinite number of states requires the use of function approximators such as backpropagation nets [16, 12, 24], we argue that these discontinuities imply severe difficulties in learning cumulative evaluation functions. The discontinuities we detected might also explain why recent applications of reinforcement learning systems to complex tasks [12] failed to show desired performance. In our conclusion, we outline some ideas to circumvent the problem. |
Year | DOI | Venue |
---|---|---|
1992 | 10.1007/BFb0019005 | GWAI |
Keywords | Field | DocType |
reinforcment learning,discontinuous q-functions,reinforcement learning | Temporal difference learning,Classification of discontinuities,Computer science,Artificial intelligence,Backpropagation,State space,Robotics,Reinforcement learning | Conference |
ISBN | Citations | PageRank |
3-540-56667-8 | 0 | 0.34 |
References | Authors | |
8 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexander Linden | 1 | 74 | 11.71 |