Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learning algorithm. The advantage is that the algorithm can then use the reward function to check the reward for states that the agent hasn't even encountered yet. In addition, the algorithm can simultaneously learn policies for multiple reward functions. For each state, the algorithm would calculate the reward using each of the reward functions and add the rewards to its experience replay dataset. The Hindsight Experience Replay algorithm developed by Andrychowicz et al. (2017) does just this, and learns to generalize across a distribution of sparse, goal-based rewards. We extend this algorithm to linearly-weighted, multi-objective rewards and learn a single policy that can generalize across all linear combinations of the multi-objective reward. Whereas other multi-objective algorithms teach the Q-function to generalize across the reward weights, our algorithm enables the policy to generalize, and can thus be used with continuous actions.

We consider the problem of detection of edges in an image by solving an anisotropic diffusion equation, which has the intrinsic property that low‐contrast regions are smoothed and high‐contrast ones are enhanced. Since wavelets are known to provide better representation of singularities (i.e., edges), a more efficient scheme than those suggested earlier for solving the diffusion equation is formulated in terms of wavelet expansions of the image. These expansions also provide a natural way of estimating the local contrast, and hence of implementing a space‐varying parameterization of the diffusion equation for improved performance. Our method can be viewed as a wavelet counterpart of standard spectral methods for solving partial differential equations. © 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 356–368, 1998

No abstract

No abstract