— This paper shows that the distributed representation found in Learning Vector Quantization (LVQ) enables reinforcement learning methods to cope with a large decision search spa...
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
Joel Veness, Kee Siong Ng, Marcus Hutter, David Si...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high...