Intrinsic curiosity module - An intrinsic curiosity module, or ICM, is a reinforcement-learning component that generates an internal reward from errors in predicting the consequences of...
Inverse reinforcement learning - Inverse reinforcement learning is the task of inferring a reward or cost function from observed behavior in a sequential decision-making setting.
Keepout - A keepout is a designated area that autonomous robot navigation should avoid or must not enter.
Lambda return - A lambda return is a weighted combination of multi-step returns used as a learning target in reinforcement learning.
Least-squares temporal-difference learning - Least-squares temporal-difference learning, usually abbreviated LSTD, estimates a value function by solving a system of equations built from observed...
Local costmap - A local costmap is a spatial representation of the area near a robot that assigns navigation costs to locations.
Localization - Localization is the process of estimating a robot's position and orientation relative to a reference frame or environment.
Markov localization - Markov localization is a probabilistic method for estimating a robot's pose by maintaining and updating a belief distribution over possible poses.
Maximum a posteriori policy optimization - Maximum a posteriori policy optimization, usually called MPO, is a reinforcement-learning method that improves a policy through alternating action...
Mean squared Bellman error - Mean squared Bellman error, abbreviated MSBE, measures how closely an approximate value function satisfies a Bellman equation.
Mean squared projected Bellman error - Mean squared projected Bellman error, abbreviated MSPBE, measures the squared distance between an approximate value function and its Bellman target after...
Mean squared temporal-difference error - Mean squared temporal-difference error is the expected square of the error between a sampled reward-plus-continuation target and the current value estimate.
Model-based reinforcement learning - Model-based reinforcement learning uses a model of an environment's consequences to help an agent learn or choose actions that maximize expected cumulative...
Model-free (reinforcement learning) - Model-free reinforcement learning learns value estimates or a policy from experience without using an explicit model of the environment's transition and...
Modified policy iteration - Modified policy iteration is a dynamic-programming method that alternates greedy policy improvement with partial policy evaluation.
Monte Carlo localization - Monte Carlo localization is a robot localization method that represents uncertainty about pose using a set of weighted samples called particles.
Morphogenetic robotics - Morphogenetic robotics uses ideas from biological morphogenesis - the processes that generate an organism's form - to design robot structures, controllers...
Motion planning - Motion planning is the process of finding a feasible movement from a robot's starting configuration to a goal while respecting relevant constraints.
Multiarmed bandit - A multiarmed bandit is a sequential decision problem in which a learner repeatedly chooses among alternatives, called arms, and observes the reward of the...
N-step Q(sigma) - N-step Q(sigma) is a family of multi-step action-value learning algorithms that mixes sampled action backups with expectations over actions.
n-step return - An n-step return is a reinforcement-learning target that combines the next n observed rewards with an estimated continuation value at the end of that horizon.
N-step tree backup - N-step tree backup is a multi-step action-value learning method that combines an observed trajectory with expected values for actions not taken.
NYQUIST PLOT - A Nyquist plot traces a system's complex frequency response as frequency varies.
Odometry - Odometry is the estimation of a robot's change in position and orientation from measurements of its motion over time.
Odor source localization - Odor source localization is the task of identifying where an airborne or waterborne chemical plume originates, using measurements gathered by sensors and...
Off-policy - Off-policy describes reinforcement learning or policy evaluation that learns about a target policy using experience generated by a different behavior policy.
Offline reinforcement learning - Offline reinforcement learning is the process of learning a decision-making policy from an existing dataset of experience without collecting additional...
On-policy - On-policy describes reinforcement learning in which the policy being evaluated or improved is also the policy used to generate the relevant experience.
One-armed bandit - A one-armed bandit is a sequential decision problem involving one uncertain reward-producing option and a known alternative, such as a fixed reward or the...
Open-source robotics - Open-source robotics develops or uses robot software, hardware designs, or both under licenses that permit access, modification, and redistribution under...
Optimal policy - An optimal policy is a decision rule that achieves the best expected return allowed by a specified decision problem.
Optimistic initial action values - Optimistic initial action values are deliberately high starting estimates of the rewards or returns available from actions.
Path consistency learning - Path consistency learning, abbreviated PCL, is a reinforcement-learning approach that jointly trains policy and value estimates to satisfy...
Perceptual robotics - Perceptual robotics studies how principles of perception can inform the design of robots and their interaction with the world.
Playout policy - A playout policy is the rule used to choose actions during a simulated continuation of a decision process, especially beyond the explicitly explored part of...
Policy - A policy is a rule that determines how an agent selects actions from the information available to it.
Policy gradient - A policy gradient is the derivative of a policy's expected performance with respect to the parameters that control its action choices.
Policy-gradient baseline - A policy-gradient baseline is a reference quantity subtracted from a return or action-value estimate when forming a policy-gradient update.
Policy improvement - Policy improvement is the process of changing a decision policy using information about the value of its actions.
Policy iteration - Policy iteration is a method for finding an improved decision policy by repeatedly alternating policy evaluation and policy improvement.
Policy loss - Policy loss is the shortfall in expected performance caused by following a particular policy instead of an optimal policy for the same decision problem.
Policy value - Policy value is the expected return obtained by following a specified policy under a specified decision problem.
PPO-Clip - PPO-Clip is the clipped-objective version of proximal policy optimization.
PPO-Penalty - PPO-Penalty is a proximal policy optimization variant that subtracts a penalty for KL divergence between the old and candidate policies from a...
Prioritized experience replay - Prioritized experience replay is a reinforcement-learning technique that samples some stored experiences more often than others according to an estimate of...
Proper policy - A proper policy is a policy that reaches the designated terminal state with probability one from the required starting states in a stochastic shortest-path...
Proximal policy optimization - Proximal policy optimization, or PPO, is a family of policy-gradient methods designed to improve a decision policy while discouraging excessively large...