Explore Reinforcement Learning through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Reinforcement Learning.
Showing 61-120 of 136 articles
Reinforcement learning (RL) is a branch of machine learning in which an agent learns to make sequential decisions by interacting with an environment and receiving feedback in the form of rewards or penalties.
A Markov Decision Process (MDP) is a mathematical framework for modeling sequential decision-making in stochastic environments.
Microduck is a small biped robot developed by Pollen Robotics, the robotics team within Hugging Face.
Misha Laskin (also published as Michael Laskin) is an AI researcher and entrepreneur best known for his work on reinforcement learning and for co-founding Reflection AI
Model soups is a weight-averaging technique (a form of model merging) that combines several independently fine-tuned neural networks into a single model by averaging their parameters.
MonoRace is an onboard perception and control system for autonomous racing drones, developed at the Micro Air Vehicle Laboratory (MAVLab) of Delft University of Technology (TU Delft) in the Netherlands.
Monte Carlo Tree Search (MCTS) is a heuristic search algorithm for sequential decision-making that finds strong actions by running many simulated playthroughs of a problem and aggregating their outcomes into a…
MuJoCo (short for Multi-Joint dynamics with Contact) is an open-source physics simulator designed for fast and accurate simulation of articulated mechanical systems with rich contact interactions.
MuZero is a model-based reinforcement learning algorithm developed by DeepMind that reached superhuman play in Go, chess, and shogi and set a new state of the art on the 57-game Atari benchmark without being…
A multi-armed bandit is a sequential decision problem in which a learner repeatedly picks one action from a fixed set, receives a random reward for that action only, and tries to accumulate as much reward as…
NVIDIA COMPASS is a framework and trained model for cross-embodiment robot navigation. Its name expands to Cross-Embodiment Mobility Policy via Residual RL and Skill Synthesis.
NVIDIA Isaac Lab is an open-source, GPU-accelerated framework for robot learning that trains robot control policies at scale by running thousands of physics simulations in parallel on GPUs.
A Nash equilibrium is a combination of strategies, one for each player in a game, such that no player can raise their own payoff by changing strategy alone while everyone else keeps theirs unchanged.
Online learning is a machine learning paradigm in which a model receives data sequentially, one example or one mini-batch at a time, and updates its parameters immediately after each observation rather than…
OpenAI Baselines is a collection of open-source, high-quality reference implementations of reinforcement learning (RL) algorithms released by OpenAI.
OpenAI Five was a reinforcement learning system developed by OpenAI to play the competitive multiplayer video game Dota 2 at a professional level.
PROWL-1 is a training framework from the AI lab Odyssey in which a reinforcement learning agent is paid to break a world model.
Pieter Abbeel (born 1977) is a Belgian-American computer scientist and a professor of electrical engineering and computer sciences at the University of California, Berkeley, where he directs the Berkeley Robot…
Pluribus is an artificial intelligence program that defeated elite human professionals at six-player no-limit Texas hold'em, the most popular form of poker played by people.
In reinforcement learning (RL), a policy is the function that maps an agent's observed state to the action it takes, defining the agent's complete strategy of behavior.
Policy gradient methods are a family of reinforcement learning algorithms that directly parameterise the agent's policy and optimise it by stochastic gradient ascent on the expected return.
A process reward model (PRM), also called a process-supervised reward model or step-level verifier, is a learned scoring model that evaluates the correctness or quality of each intermediate step in a large…
Proximal Policy Optimization (PPO) is an on-policy policy gradient reinforcement learning algorithm that stabilizes training by clipping the policy update so the new policy stays close ("proximal") to the old…
The Q-function, also called the action-value function or state-action value function and written…
Q-learning is a model-free, off-policy reinforcement learning algorithm that learns the value of taking a given action in a given state by iteratively updating an action-value function Q(s, a), the expected…
Quiet-STaR is a self-supervised training method that teaches a large language model to generate short, token-level internal "thoughts," or rationales, that help it predict the text that follows
RAGEN-2 is a 2026 research paper and public code extension for diagnosing and mitigating reasoning collapse during reinforcement learning of multi-turn large language model agents.
Reinforcement Learning from AI Feedback (RLAIF) is a family of alignment techniques for large language models in which the preference labels used to fine-tune a model are produced by another AI system
RLOO (REINFORCE Leave-One-Out) is an online reinforcement learning algorithm for aligning large language models with reward signals such as those derived from human preferences.
Reinforcement Learning with Verifiable Rewards (RLVR) is a post-training paradigm for large language models in which the reward signal comes from a deterministic
A random policy is a reinforcement learning policy that chooses actions from a fixed probability distribution, most commonly the uniform distribution, independent of the current state and of any learned value…
ReST (Reinforced Self-Training) is a family of self-training algorithms for large language models that improve a model by fine-tuning it on its own filtered outputs instead of on additional human-written data.
Recursive reward modeling (RRM) is a proposed approach to the scalable oversight problem in AI alignment
Reflex is a research framework for visually reactive whole-body control of a Unitree G1 humanoid.
Reinforcement learning (RL) is a branch of machine learning in which an agent learns to make decisions by taking actions in an environment to maximize a cumulative reward signal, discovering good behavior…
A replay buffer (also called an experience replay buffer or replay memory) is a fixed-size memory that stores an off-policy reinforcement learning agent's past transitions, each a tuple of state, action…
In reinforcement learning, the return…
In reinforcement learning (RL), a reward is a scalar feedback signal that an environment sends to an agent after each action, quantifying how desirable that action's outcome was
A reward model (RM) is a model trained to score the outputs of another AI system, producing a scalar estimate of how good a candidate response is according to some standard, most often human preference.
Reward hacking (also called specification gaming) is a failure mode in artificial intelligence in which a system maximizes its given objective or reward signal through unintended shortcuts, exploits, or…
RewardBench is a benchmark and public leaderboard for evaluating reward models, the scoring functions that sit at the center of reinforcement learning from human feedback (RLHF).
Richard Stuart Sutton (born 1957 or 1958) is a Canadian-American computer scientist regarded as one of the founders of modern computational reinforcement learning, and a co-recipient, with Andrew G. Barto
River AI (legally River AI Inc.) is an American artificial intelligence company based in Palo Alto, California, founded in 2026 by Igor Babuschkin, a co-founder of xAI.
Robot learning studies how robots acquire or improve behavior from data and experience.
Robotics models are machine learning systems that give robots the ability to perceive their surroundings, plan actions, and execute motor control.
SARSA (State-Action-Reward-State-Action) is an on-policy temporal-difference (TD) control algorithm that learns the action-value function Q^pi(s, a) of the policy an agent is actually following
SONIC, short for Supersizing mOtion tracking for Natural humanoId Control, is a physics-based whole-body motion tracking and control system developed by Nvidia.
SPADE, short for Self-Play in Adaptive Synthetic Executable Environments, is a reinforcement-learning framework in which one language model alternates between designing executable training environments and…
STaR (Self-Taught Reasoner) is a self-training method that teaches a large language model to reason by having it generate its own chain-of-thought rationales, keeping only the rationales that lead to correct…
Selective Language Modeling (SLM) is a pretraining objective for language models that applies the training loss to only a chosen subset of tokens rather than to every token in the corpus.
Sergey Levine is a computer scientist, associate professor of electrical engineering and computer sciences at the University of California, Berkeley, and a co-founder of Physical Intelligence
Sim-to-real transfer (also written as sim2real) is the process of training a policy, controller, or perception model inside a physics simulator and deploying it on a physical robot in the real world without…
Simulation in artificial intelligence and robotics is the use of computational physics, rendering, and procedural environments to recreate a synthetic version of a physical or virtual world inside which AI…
SkyRL is an open-source reinforcement learning (RL) library for post-training large language models and multi-turn agents.
Soft Actor-Critic (SAC) is an off-policy, maximum-entropy deep reinforcement learning algorithm that trains a stochastic actor-critic to maximize expected reward plus the entropy of its own policy, so the…
Sparse upcycling is a technique for building a sparsely activated mixture of experts (MoE) model by initializing it from an already trained dense Transformer checkpoint
Specification gaming is the phenomenon in which an optimizer satisfies the literal specification of an objective without producing the outcome that the designer actually wanted.
Spinning Up in Deep RL is a free, open-source educational resource produced by OpenAI to make deep reinforcement learning (deep RL) easier to learn.
In reinforcement learning (RL), a state is a complete description of the environment at a particular point in time, containing all the information an agent needs to choose its next action.
The state-action value function, written Q^π(s, a) and also called the action-value function or Q-function, gives the expected discounted return an agent obtains by taking action a in state s and thereafter…