Q-learning - Q-learning is a model-free reinforcement learning method that updates estimates of the long-term value of taking actions in states.
R-learning - R-learning is an off-policy reinforcement-learning control method for continuing tasks with an average-reward objective.
Random network distillation - Random network distillation (RND) is an exploration method that gives a reinforcement-learning agent an intrinsic reward based on prediction error.
Random policy - A random policy is a reinforcement learning action-selection rule that uses chance to choose what the agent does.
Reinforcement - Reinforcement is evaluative feedback that influences how an agent learns from its behavior.
Reinforcement learning - Reinforcement learning is a machine learning approach in which an agent learns how to act from experience evaluated through rewards.
Reinforcement Learning from Human Feedback - Reinforcement Learning from Human Feedback, commonly abbreviated RLHF, is a family of methods that uses human evaluations to guide reinforcement learning.
Relational reinforcement learning - Relational reinforcement learning combines reinforcement learning with representations of objects and the relationships between them.
Replacing eligibility trace - A replacing eligibility trace is a short-term credit-assignment record that is reset to a fixed active value, usually one, whenever its state or feature is...
Residual-gradient reinforcement learning - Residual-gradient reinforcement learning updates a value approximator by differentiating a squared Bellman-style residual through both the current...
Retrace(lambda) - Retrace(lambda) is a multi-step off-policy reinforcement-learning method that combines target-policy temporal-difference errors using truncated...
Reward - A reward is the numerical feedback signal that defines what a reinforcement learning agent is encouraged to achieve.
Reward hypothesis - The reward hypothesis is the proposal that goals and purposes can be represented through maximizing the expected cumulative value of a scalar reward signal.
Reward shaping - Reward shaping adds supplementary reward information to a reinforcement learning task to guide learning.
Reward-to-go - Reward-to-go is the cumulative reward remaining from a particular decision onward in a trajectory.
Robot as a service - Robot as a service, often abbreviated RaaS and also called robots or robotics as a service, commonly describes obtaining robotic capability through a...
Robot navigation - Robot navigation is the process of guiding a mobile robot through an environment to reach a destination or accomplish a movement task.
Robot tax - A robot tax is a proposed or analyzed tax aimed at automation, robotic capital, or some economic gains associated with replacing human tasks.
Robotic governance - Robotic governance concerns how people and institutions guide, oversee, and remain accountable for the development and use of robotics, automation, and...
Robotics - Robotics is the field concerned with designing, building, programming, controlling, and using robots.
Safe policy iteration - Safe policy iteration is a family of reinforcement-learning and approximate dynamic-programming methods that choose policy updates by maximizing a lower...
SARSA(lambda) - SARSA(lambda) is an on-policy reinforcement-learning control method that extends one-step SARSA with eligibility traces.
Scenario (vehicular automation) - In vehicular automation, a scenario describes how a traffic setting and its participants evolve over time, including relevant actions, events, and...
Semi-gradient temporal-difference learning - Semi-gradient temporal-difference learning updates a parameterized value estimate using a bootstrapped target while treating that target as constant during...
Sequential decision making - Sequential decision making concerns choosing actions over time when present choices influence future conditions, information, or opportunities.
Simultaneous localization and mapping - Simultaneous localization and mapping, usually shortened to SLAM, is the problem of estimating a robot's location while building a map of the environment...
Situated robotics - Situated robotics studies and designs robots as agents whose behavior arises through ongoing interaction with their environment.
Smoothed Bellman error embedding - Smoothed Bellman error embedding, or SBEED, is a reinforcement-learning method that combines an entropy-smoothed Bellman equation with a primal-dual...
Soft actor-critic - Soft actor-critic, or SAC, is an off-policy actor-critic reinforcement-learning algorithm that optimizes expected reward together with a policy-entropy term.
Statement - In this robotics knowledge-base context, a Statement is a structured assertion represented as a subject, predicate, and object triple.
Stochastic multiarmed bandit - A stochastic multiarmed bandit is a sequential decision problem in which a learner repeatedly chooses among actions with uncertain rewards.
Stochastic policy - A stochastic policy specifies a probability distribution over actions for each relevant state or observation.
Stt - stt stands for speech-to-text: the process of converting spoken audio into written text. It is commonly called automatic speech recognition, or ASR.
SWARM ROBOTICS - SWARM ROBOTICS studies how groups of robots can produce useful collective behavior through interactions among their members and with the environment.
Tabular Q-learning - Tabular Q-learning is Q-learning implemented with an explicit table of action-value estimates, one entry for each represented state-action pair.
Target policy smoothing - Target policy smoothing is a reinforcement-learning technique that perturbs the next action used in a critic's learning target, encouraging value learning...
Teleoperation - Teleoperation is the remote operation of a robot or machine by a human, using commands sent through a communication link and feedback from the remote system.
Temporal-difference error - A temporal-difference error, often shortened to TD error and written delta, is the difference between a bootstrapped learning target and the current value...
Temporal-difference learning with gradient correction - Temporal-difference learning with gradient correction, usually called TDC, is a linear value-prediction algorithm that adds an auxiliary correction to the...
Trajectory - In reinforcement learning, a trajectory is an ordered sequence of interactions between an agent and its environment.
Tree selection policy - A tree selection policy is a rule for choosing which branch to follow while traversing a search tree.
True online TD(lambda) - True online TD(lambda) is a temporal-difference prediction algorithm whose efficient backward-view updates exactly match a specified online forward view for...
Trust region policy optimization - Trust region policy optimization, or TRPO, is a policy-gradient reinforcement-learning method that seeks an improved policy while limiting how much its...
UNCANNY VALLEY - The uncanny valley is a proposed pattern in people's responses to humanlike artificial characters or robots: increasing human resemblance may initially...
V-trace - V-trace is an off-policy multi-step target construction for state-value learning, introduced with the IMPALA distributed actor-learner architecture.
ValueDICE - ValueDICE is an imitation-learning algorithm that learns a policy by matching its discounted state-action distribution to an expert's distribution through...