Results for "model-based"
Model-Based RL
AdvancedRL using learned or known environment models.
Model-based reinforcement learning is like having a map while exploring a new city. Instead of wandering around aimlessly, you can look at the map to plan your route and make better decisions about where to go next. In this type of learning, an AI agent first learns how the environment works—like...
Graphs containing multiple node or edge types with different semantics.
Compromising AI systems via libraries, models, or datasets.
Diffusion performed in latent space for efficiency.
Model that compresses input into latent space and reconstructs it.
Autoencoder using probabilistic latent variables and KL regularization.
Pixel-wise classification of image regions.
Transformer applied to image patches.
Attention between different modalities.
Recovering 3D structure from images.
Detects trigger phrases in audio streams.
Generates audio waveforms from spectrograms.
Models effects of interventions (do(X=x)).
Low-latency prediction per request.
Centralized repository for curated features.
Agents communicate via shared state.
Scaling law optimizing compute vs data.
Matrix of first-order derivatives for vector-valued functions.
Direction of steepest ascent of a function.
Measure of vector magnitude; used in regularization and optimization.
Describes likelihoods of random variable outcomes.
Variable whose values depend on chance.
Average value under a distribution.
Measure of spread around the mean.
Normalized covariance.
Probability of data given parameters.
Minimum relative to nearby points.
Restricting updates to safe regions.
Model exploits poorly specified objectives.
Model optimizes objectives misaligned with human values.
Sampling multiple outputs and selecting consensus.