Action (Reinforcement Learning)
In reinforcement learning (RL), an action is a decision or move made by an agent that affects the state of the environment.
Reinforcement Learning
Explore Reinforcement Learning through related topics and the articles other pages reference most.
Most linked
The Reinforcement Learning articles that other AI Wiki pages link to most.
- Reinforcement learningReinforcement learning (RL) is a branch of machine learning in which an agent learns to make decisions by taking actions in an environment…
- Embodied AIEmbodied AI is an area of artificial intelligence concerned with agents whose perception, action, learning, and reasoning are coupled…
- Imitation LearningImitation learning is a family of methods for learning sequential behavior from demonstrations.
- Reward ModelA reward model (RM) is a model trained to score the outputs of another AI system, producing a scalar estimate of how good a candidate…
- Robot learningRobot learning studies how robots acquire or improve behavior from data and experience.
- Sim-to-real transferSim-to-real transfer (also written as sim2real) is the process of training a policy, controller, or perception model inside a physics…
- Reward hackingReward hacking (also called specification gaming) is a failure mode in artificial intelligence in which a system maximizes its given…
- MuJoCoMuJoCo (short for Multi-Joint dynamics with Contact) is an open-source physics simulator designed for fast and accurate simulation of…
Explore articles
Browse subtopics (42)
Articles that also belong to these categories. Counts cover all of Reinforcement Learning.
All articles (126)Machine Learning (58)Robotics (19)Deep Learning (12)Google DeepMind (12)People (12)AI Models (9)AI Research (8)AI in Gaming (8)Algorithms (8)Training & Optimization (8)AI Agents (7)Artificial Intelligence (7)Open Source AI (7)Chinese AI (6)OpenAI (6)AI Alignment (5)AI Safety (5)Mathematics (5)Embodied AI (4)Large Language Models (4)World Models (4)AI Inference (3)NVIDIA (3)AI Benchmarks (2)Meta AI (2)Model Evaluation (2)Reasoning Models (2)Robot Hardware (2)Statistics (2)AI Code Generation (1)AI Companies (1)AI Hardware (1)AI Infrastructure (1)Computer Science (1)Developer Tools (1)Generative AI (1)Google (1)Humanoid Robots (1)Image Generation (1)Multimodal AI (1)Physical AI (1)Research Organizations (1)
Showing 1-60 of 126 articles
Actor-critic methods
Actor-critic methods are a family of reinforcement learning algorithms that learn two things at once: a parameterized policy, called the actor, which chooses actions, and a value function, called the critic
Agent57
Agent57 is a model-free distributed reinforcement learning algorithm developed by Google DeepMind and reported in 2020.
Agora-1
Agora-1 is a multi-agent world model released by the AI lab Odyssey on 18 May 2026.
AlphaChip
AlphaChip is a reinforcement-learning method developed by Google DeepMind for designing the physical layout of computer chips, specifically the placement of large circuit components known as macros.
AlphaDev
AlphaDev is an artificial intelligence system built by Google DeepMind that used deep reinforcement learning to discover faster algorithms for common computing tasks, most notably small-scale sorting and…
AlphaGo
AlphaGo is a computer program developed by DeepMind that plays the board game Go, and it was the first artificial intelligence to defeat a professional human Go player on a full 19x19 board without a handicap.
AlphaGo Zero
AlphaGo Zero is a Go-playing computer program developed by DeepMind that reached a superhuman level entirely through self-play reinforcement learning, starting from random play with no human game data.
AlphaStar
AlphaStar is an artificial intelligence system built by Google DeepMind that in 2019 became the first AI to reach Grandmaster level in the real-time strategy game StarCraft II
AlphaTensor
AlphaTensor is an artificial-intelligence system from DeepMind that uses deep reinforcement learning to discover faster algorithms for matrix multiplication.
AlphaZero
AlphaZero is a general-purpose reinforcement learning algorithm developed by DeepMind that taught itself to play chess, shogi (Japanese chess), and Go at a superhuman level from scratch, using only the rules…
Andrew Barto
Andrew Barto is an American computer scientist and one of the founders of modern reinforcement learning, the branch of machine learning in which an agent learns by trial and error from rewards.
Behavioral Cloning
Behavioral cloning is the approach to imitation learning that reduces control to a supervised learning problem.
Bellman Equation
The Bellman equation is a recursive formula stating that the value of a state equals the immediate reward received there plus the discounted value of the next state
Best-of-N sampling
Best-of-N sampling (BoN) is an inference-time method that improves a large language model output by drawing N independent candidate responses to the same prompt, scoring each with a reward model, verifier, or…
CodeMidas
CodeMidas is an agentic data pipeline from Xiaomi's LLM Core team that turns functionality already implemented in open-source codebases into executable reinforcement learning environments for coding agents.
Control theory
Control theory is the mathematical and engineering discipline concerned with designing and analysing systems that achieve desired behaviour through measurement and feedback.
Critic
A critic in reinforcement learning (RL) is the component of an actor-critic system that estimates a value function, scoring how good the actor's chosen actions are and converting that judgment into a…
DAPO (Decoupled Clip and Dynamic Sampling Policy Optimization)
DAPO, short for Decoupled Clip and Dynamic sAmpling Policy Optimization, is an open-source reinforcement learning algorithm and training system for large language models, introduced in March 2025 by…
DARE (Drop And REscale)
DARE (Drop And REscale) is a training-free preprocessing technique for model merging that sparsifies the parameter changes introduced by fine-tuning before those changes are combined across several models.
DDPG (Deep Deterministic Policy Gradient)
DDPG (Deep Deterministic Policy Gradient) is an off-policy, model-free actor-critic algorithm in deep reinforcement learning that learns continuous-control policies by combining a deterministic actor with a…
DQN
The Deep Q-Network (DQN) is a model-free, off-policy reinforcement learning algorithm that combines Q-learning with a deep neural network function approximator, learning to act directly from raw pixels.
Dactyl (OpenAI)
Dactyl was a robotics research project at OpenAI that used deep reinforcement learning to control a five-fingered, human-like robot hand and manipulate physical objects with high dexterity.
David Silver
David Silver is a British computer scientist whose work has defined the modern field of deep reinforcement learning and computer game-playing.
Deep Q-Network (DQN)
Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function)
DeepSeek Elastic Compute (DSec)
DeepSeek Elastic Compute (DSec) is the production sandbox platform that DeepSeek uses to run the isolated execution environments behind agentic reinforcement learning (RL) training and evaluation of its…
Depth up-scaling (DUS)
Depth up-scaling (DUS) is a model-scaling method that builds a deeper large language model by duplicating and stacking the layers of an existing pretrained Transformer checkpoint and then continuing to…
Discount Factor
The discount factor, almost always written as the Greek letter…
DoReMi
DoReMi (Domain Reweighting with Minimax Optimization) is a method for automatically choosing the proportions, or "domain weights," of each data source in a pretraining corpus for a large language model.
Dreamer (reinforcement learning)
Dreamer is a family of model-based reinforcement learning agents that learn a compact world model of their environment and then improve their behavior by "imagining" sequences of future outcomes inside that…
Embodied AI
Embodied AI is an area of artificial intelligence concerned with agents whose perception, action, learning, and reasoning are coupled through interaction with an environment.
Environment
In reinforcement learning (RL), an environment is the external system that an agent interacts with: it receives the agent's actions, transitions to a new state, and returns an observation together with a…
Episode (Reinforcement Learning)
An episode in reinforcement learning is one complete sequence of interaction between an agent and its environment, starting from an initial state and ending when a terminal state is reached.
Epsilon Greedy Policy
The epsilon-greedy policy (also written as ε-greedy) is a simple action-selection rule for reinforcement learning and multi-armed bandit problems: with probability 1 - ε the agent picks the action with the…
Evol-Instruct
Evol-Instruct is a method for automatically generating large instruction tuning datasets by prompting a large language model to rewrite
Experience Replay
Experience replay is a reinforcement learning technique in which an agent stores its past transitions in a memory called a replay buffer and samples random mini-batches of those stored transitions to train on
GRPO
Group Relative Policy Optimization (GRPO) is a reinforcement learning algorithm for fine-tuning large language models that eliminates the separate critic (value) network used by PPO
Gato (DeepMind)
Gato is a single generalist AI agent built by DeepMind and described in the May 2022 paper "A Generalist Agent" (arXiv:2205.06175).
Generalist GEN-1
GEN-1 is an embodied robot foundation model and control system developed by Generalist AI.
Greedy Policy
In reinforcement learning, a greedy policy is a decision rule that, in every state, selects the action with the highest estimated value.
Group Sequence Policy Optimization (GSPO)
Group Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm for training large language models, introduced by the Qwen team at Alibaba in July 2025.
Gym (OpenAI Gym / Gymnasium)
Gym, often written as OpenAI Gym, is an open source Python toolkit for developing and comparing reinforcement learning algorithms, originally released by openai on April 27, 2016.
HuggingFace TRL
TRL (Transformer Reinforcement Learning, now stylized as Transformers Reinforcement Learning) is an open-source Python library maintained by Hugging Face for post-training large language models with…
Imitation Learning
Imitation learning is a family of methods for learning sequential behavior from demonstrations.
Importance sampling
Importance sampling (often abbreviated IS) is a Monte Carlo method for estimating the expectation of a function under a target probability distribution…
Instruction backtranslation (Humpback)
Instruction backtranslation is a self-alignment method for generating instruction tuning data, introduced by researchers at Meta AI in the paper "Self-Alignment with Instruction Backtranslation," first posted…
Intrinsic Discovery (Induction Labs)
Intrinsic Discovery is an experimental training method introduced by Induction Labs in August 2026.
Ioannis Antonoglou
Ioannis Antonoglou is a Greek artificial intelligence researcher known as a co-creator of several of the landmark reinforcement learning systems built at Google DeepMind, including the Atari-playing Deep…
IronBench
IronBench is a research environment and evaluation for training a large language model to propose medium-power-transformer designs. General Trajectory introduced the project in September 2026.
Jeff Clune
Jeff Clune is a computer scientist known for research on open-endedness, evolutionary algorithms, deep reinforcement learning, and what he calls "AI-generating algorithms" (AI-GAs)
Joelle Pineau
Joelle Pineau (born 1974) is a Canadian computer scientist who is the first Chief AI Officer of Cohere, a professor and William Dawson Scholar at McGill University, and a core academic member of Mila.
John Schulman
John Schulman is an American artificial intelligence researcher, one of the eleven original co-founders of OpenAI, and the inventor of Proximal Policy Optimization (PPO), the reinforcement-learning algorithm…
Jumper (Robot)
Jumper is a crab-inspired robot from KingKong Robotics with 22 degrees of freedom.
KTO
KTO (Kahneman-Tversky Optimization) is a method for aligning large language models with human feedback using only a binary signal of whether a model output is desirable or undesirable, rather than the paired…
Kimi K1.5
Kimi K1.5 is a multimodal reasoning large language model developed by Moonshot AI, a Beijing-based artificial intelligence company.
Luo Fuli
Luo Fuli (Chinese: 罗福莉; also written Fuli Luo) is a Chinese AI researcher who leads the MiMo large-model team at Xiaomi.
Machine learning terms/Reinforcement Learning
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.
Markov Decision Process (MDP)
A Markov Decision Process (MDP) is a mathematical framework for modeling sequential decision-making in stochastic environments.
Microduck
Microduck is a small biped robot developed by Pollen Robotics, the robotics team within Hugging Face.
Misha Laskin
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