Corpus ID: 229331898

Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent

@inproceedings{Schaldenbrand2021ContentML,
  title={Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent},
  author={Peter Schaldenbrand and Jean Oh},
  booktitle={AAAI},
  year={2021}
}
The objective of most Reinforcement Learning painting agents is to minimize the loss between a target image and the paint canvas. Human painter artistry emphasizes important features of the target image rather than simply reproducing it (DiPaola 2007). Using adversarial or L2 losses in the RL painting models, although its final output is generally a work of finesse, produces a stroke sequence that is vastly different from that which a human would produce since the model does not have knowledge… Expand

References

SHOWING 1-10 OF 20 REFERENCES
StrokeNet: A Neural Painting Environment
Learning to Paint With Model-Based Deep Reinforcement Learning
Neural Painters: A learned differentiable constraint for generating brushstroke paintings
Continuous control with deep reinforcement learning
Improved Techniques for Training GANs
...
1
2
...