Results for "parameter estimation"

Bayesian parameter estimation using the mode of the posterior distribution.

Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

The shape of the loss function over parameter space.

Combines value estimation (critic) with policy learning (actor).

Pixel motion estimation between frames.

Monte Carlo method for state estimation.

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Using same parameters across different parts of a model.

Estimating parameters by maximizing likelihood of observed data.

Approximating expectations via random sampling.

Inferring the agent’s internal state from noisy sensor data.