Computer vision

ShortFull
CVcomputer vision
FOVfield of view

Dynamics

ShortFull
CGcenter of gravity

Frames

ShortFull
DCMdirection cosine matrix

Probability

ShortFull
RVrandom variable
PDFprobability density function
KLKullback-Leibler
GPGaussian process

Neural networks

ShortFull
MTSmultivariate time series
LSTMlong short-term memory
NNneural network
CNNconvolutional neural network
MLPmultilayer perceptron
ReLUrectified linear unit
SGDstochastic gradient descent
GRUgated recurrent unit
RNNrecurrent neural network

Reinforcement learning

ShortFull
RLreinforcement learning
RLHFreinforcement learning from human feedback
DAggerdataset aggregation
gSDEgeneralized state-dependent exploration
AMPadversarial motion priors
MDPMarkov decision process
SACSoft Actor-Critic
SARSAState, Action, Reward, State, Action
TDtemporal difference
GLIEgreedy in the limit with infinite exploration
DQNDeep -Network
DDQNDouble DQN
TRPOTrust-Region Policy Optimization
PPOProximal Policy Optimization
DDPGDeep Deterministic Policy Gradient
TD3Twin Delated Deep Deterministic Policy Gradient