Policy Function
A mapping function from states to actions in reinforcement learning, usually parameterized by a neural network. After training, the inference stage requires only a single forward pass to output an action, making it computationally efficient.
Timeline (last 90 days)
The learned policy function maps the current posterior belief about the image directly to the next optimal binary measurement pattern, making inference computationally efficient and avoiding online optimization.
The policy function is usually parameterized by a neural network, and during training the sequential measurement process is simulated and policy gradient or Actor-Critic optimization is performed with EIG as the reward.
All Facts (2)
The learned policy function maps the current posterior belief about the image directly to the next optimal binary measurement pattern, making inference computationally efficient and avoiding online optimization.
50%UnverifiedThe policy function is usually parameterized by a neural network, and during training the sequential measurement process is simulated and policy gradient or Actor-Critic optimization is performed with EIG as the reward.
50%