reinforcement learning
57 episodes mention this concept
ChrisWillxMar 31, 2026The Alibaba AI Incident and the Terrifying Reality of Autonomous AI Behavior
TechnologyAI SafetyAutonomous Tool UseReinforcement Learning OptimizationAI Self-Replication
hubermanlabFeb 2, 2026How Dopamine & Serotonin Shape Decisions, Motivation & Learning: Beyond Reward to Continuous Expectation Updating
NeuroscienceDopamineSerotoninNeuromodulatorsMotivation
lexfridmanJan 31, 2026The State of AI in 2026: LLMs, Geopolitics, and the Future of Human-AI Collaboration
TechnologyDeepSeek momentOpen-weight modelsClosed-weight modelsLarge Language Models (LLMs)- lexfridmanJul 23, 2025
Demis Hassabis on AI's Capacity to Model Nature, Simulate Reality, and Revolutionize Video Games
TechnologyClassical learning algorithmsNonlinear dynamical systemsFluid dynamicsNavier-Stokes equations - hubermanlabMay 29, 2025
The Philosophical and Practical Dimensions of AI: From Self-Supervised Learning to Human-Robot Relationships
TechnologyArtificial Intelligence (AI)Machine Learning (ML)Deep LearningNeural Networks - hubermanlabFeb 17, 2025
The Primate Brain: How Hormones, Hierarchies, and Foraging Instincts Drive Human Decision-Making and Attention
NeuroscienceDecision-makingValuationHormones (impact on decision-making)Hierarchies (power dynamics) - lexfridmanFeb 3, 2025
DeepSeek, OpenAI, and the Geopolitics of AI: A Technical Dive into Open Weights, Reasoning Models, and Efficiency
TechnologyMixture of Experts (MoE)Open WeightsChain of Thought ReasoningPre-training - hubermanlabNov 18, 2024
How Simple Algorithms, Dopamine, and AI Drive Learning and Motivation in the Brain
NeuroscienceComputational NeuroscienceAlgorithmsLarge Language Models (LLMs)Artificial Intelligence (AI) - lexfridmanNov 11, 2024
Dario Amodei on AI Scaling Laws, AGI Timelines, Claude's Evolution, and the Imperative of AI Safety
TechnologyScaling LawsScaling HypothesisLarge Language Models (LLMs)Artificial General Intelligence (AGI) - lexfridmanJun 29, 2023
George Hotz on AI, Consciousness, the Future of Humanity, and the Biological vs. Silicon Stacks of Life
TechnologyWireheadingComputational complexity (P vs NP)Large Language Models (LLMs)Reinforcement Learning with Human Feedback (RLHF) - lexfridmanJun 22, 2023
Marc Andreessen on the Future of AI, Search, Content, and Truth in the Digital Age
TechnologyAI assistantsNatural language interface10 Blue LinksSemantic web - lexfridmanApr 21, 2023
Manolis Kellis on Human Irreplaceability, Evolutionary Layers, and AI as the Next Stage of Information Processing
ScienceAI AlignmentHuman IrreplaceabilityEvolutionary BaggageCognitive Layer - lexfridmanMar 30, 2023
Eliezer Yudkowsky on the Existential Dangers of AI and the End of Human Civilization
TechnologySuperintelligent AGIAI AlignmentAI ConsciousnessQualia - lexfridmanJul 12, 2022
Demis Hassabis on AI, Chess Strategy, and AlphaZero's Immortal Games
TechnologyMultiple agents (cognitive model)English opening (chess)Middle game (chess)End game (chess) - lexfridmanJul 1, 2022
Demis Hassabis on AGI, the Turing Test, and Games as the Crucible of Intelligence
TechnologyArtificial General Intelligence (AGI)Turing TestGeneralizabilityReinforcement Learning - lexfridmanJan 22, 2022
Yann LeCun on Self-Supervised Learning, World Models, and the Dark Matter of Intelligence
TechnologySelf-supervised learning (SSL)Supervised learningReinforcement learningWorld models - lexfridmanDec 12, 2021
AI Engines on an Infinite Chessboard: Exploring Generalizability and Emergent Complexity
TechnologyAI enginesinfinite chessboard8x8 subsetmeta-game - lexfridmanNov 23, 2021
Kevin Systrom on Instagram's Origin, Product Market Fit, and Data-Driven Design
TechnologyProduct-market fitCheck-in appsPhoto sharingIterative product development - hubermanlabJul 19, 2021
The Future of Human-Machine Interaction: AI, Learning, and the Dance with Robots with Dr. Lex Fridman
TechnologyArtificial Intelligence (AI)Machine Learning (ML)Deep LearningNeural Networks 
NewEconomicThinkingJun 16, 2021The Human Advantage: Framing, Mental Models, and AI in a Complex World
PhilosophyMental Models (Frames)Cognitive PsychologyBig DataMachine Learning- lexfridmanJan 18, 2021
Max Tegmark on AI, Physics, and the Quest for Intelligible Intelligence
ScienceArtificial General Intelligence (AGI)Existential risks of AIIntelligible intelligenceBlack box AI systems - lexfridmanDec 13, 2020
Michael Littman on Reinforcement Learning, AI's Future, and Dispelling Superintelligence Fears
TechnologyReinforcement LearningArtificial Intelligence (AI)Machine LearningArtificial General Intelligence (AGI) - lexfridmanJul 14, 2020
Bridging the Intelligence Gap: Sergey Levine on Robotics, Deep Learning, and the Nature of Intelligence
ScienceDeep LearningReinforcement LearningRoboticsComputer Vision - lexfridmanJul 3, 2020
The Unified Science of Mind and Brain: Bridging Psychology, Neuroscience, and AI with Matt Botvinick
NeuroscienceCognitive psychologyComputational neuroscienceArtificial intelligenceDeep learning - lexfridmanJun 26, 2020
Sophia, AGI, and the Ethics of Anthropomorphic Robotics: A Conversation with Ben Goertzel
TechnologyArtificial General Intelligence (AGI)Computational CompassionSingularityHardware Ecosystem - lexfridmanMay 10, 2020
The Unification of AI Modalities: Vision, Language, and Reinforcement Learning, and the Elusive Definition of 'Hardness' in AI
TechnologyDeep LearningComputer VisionNatural Language Processing (NLP)Reinforcement Learning (RL) - lexfridmanMay 9, 2020
Ilya Sutskever on Building AGI: Self-Play, Simulation, Consciousness, and Human Control
TechnologyArtificial General Intelligence (AGI)Deep LearningSelf-playReinforcement Learning (RL) - lexfridmanMay 8, 2020
Ilya Sutskever on the Deep Learning Revolution, AI's Unity, and the Future of Intelligence
TechnologyDeep Learning RevolutionNeural NetworksBackpropagationHessian-free optimizer - lexfridmanApr 3, 2020
David Silver on AlphaGo, AlphaZero, and the Reinforcement Learning Path to Artificial Intelligence
TechnologyReinforcement Learning (RL)Deep Reinforcement LearningAlphaGoAlphaZero - lexfridmanFeb 26, 2020
Marcus Hutter on AIXI, Kolmogorov Complexity, and the Computable Universe
TechnologyAIXI modelArtificial General Intelligence (AGI)Kolmogorov complexitySolomonoff induction - lexfridmanFeb 21, 2020
Andrew Ng's Expert Advice on Getting Started and Building a Career in Deep Learning and AI
TechnologyDeep LearningMachine LearningNeural NetworksGradient Descent - lexfridmanJan 10, 2020
Deep Learning: State of the Art in 2020, Key Advancements, Limitations, and Future Research
TechnologyDeep LearningNeural NetworksPerceptron (single-layer, multi-layer)Backpropagation - lexfridmanOct 9, 2019
Machine Learning at Spotify: The Power of User-Generated Playlists for Personalized Music Discovery
TechnologyReinforcement learningState spaceProgramming language (playlists)Meta-programming language - lexfridmanSep 13, 2019
George Hotz on Winning, Reinforcement Learning, and Discovering Life's Universal Reward Function
TechnologyReinforcement learningIntelligent agentCompressive model of the worldMaximally compressive - lexfridmanSep 5, 2019
George Hotz's Three Problems of Autonomous Driving: Static, Dynamic, and Counterfactual AI Challenges
TechnologyStatic driving problemDynamic driving problemCounterfactual driving problemMapping and localization - lexfridmanJun 3, 2019
TensorFlow's Evolution: From Google Brain's Inception to a Global Open-Source ML Ecosystem
TechnologyDeep LearningTensorFlowOpen SourceGoogle Brain - lexfridmanApr 18, 2019
Ian Goodfellow on Generative Adversarial Networks, Deep Learning Limitations, and the Future of AI Cognition
TechnologyGenerative Adversarial Networks (GANs)Deep LearningRepresentation LearningMachine Learning - lexfridmanApr 3, 2019
Greg Brockman on OpenAI, AGI, and Shaping the Future of Intelligence
TechnologyArtificial General Intelligence (AGI)Deep LearningReinforcement LearningValue Alignment - lexfridmanMar 12, 2019
Leslie Kaelbling on Reinforcement Learning, Planning, Robotics, and the Philosophy of AI
TechnologyReinforcement LearningPlanning (AI)Robot NavigationArtificial Intelligence (AI) - lexfridmanFeb 12, 2019
Taming the Long Tail: Waymo's Machine Learning Approach to Autonomous Driving Challenges
TechnologyAutonomous drivingMachine learningDeep learningPerception (AV) - lexfridmanJan 19, 2019
Tomaso Poggio on Brains, Minds, Machines, and the Nature of Intelligence
ScienceTheory of RelativityGedanken experimentArtificial General Intelligence (AGI)Biological neural networks - lexfridmanApr 25, 2018
Ilya Sutskever on Deep Learning Foundations, Meta-Learning, and Self-Play for AGI
TechnologyDeep Learning PrinciplesGeneralization Theory (shortest program)Computational Intractability (program search)Backpropagation (circuit search) - lexfridmanJan 25, 2018
Deep Reinforcement Learning: From Raw Data to Reasoning and Real-World Action
TechnologyDeep Reinforcement Learning (DRL)Artificial Intelligence (AI) stackEnd-to-end learningSupervised Learning - lexfridmanSep 27, 2016
Deep Reinforcement Learning: Core Methods, Applications, and Policy Gradients
TechnologyDeep Reinforcement Learning (DRL)Reinforcement Learning (RL)Neural NetworksFunction Approximators - lexfridman
AlphaZero, Self-Play, and the Path to General AI
TechnologySelf-playReinforcement LearningAlphaGo ZeroAlphaZero - lexfridman
Oriol Vinyals on Generalist AI Agents, AGI, and the Future of Deep Learning
TechnologyNeural NetworksDeep LearningArtificial General Intelligence (AGI)Reinforcement Learning - lexfridman
AI's Superhuman Strategy: Nash Equilibrium in Poker and Diplomacy with Noam Brown
TechnologyGame TheoryNash EquilibriumSelf-playCounterfactual Regret Minimization (CFR) - lexfridman
The Business and Philosophy of Machine Learning: Promise, Limitations, and the Quest for General Intelligence
TechnologyMachine LearningArtificial Intelligence (AI)Deep LearningSupervised Learning - lexfridman
Reverse Engineering Human Intelligence for Advanced AI and AGI: A Cognitive Science Approach
ScienceArtificial General Intelligence (AGI)AI TechnologiesDeep LearningPattern Recognition - lexfridman
MIT AGI: Engineering Intelligence - Bridging Theory, Practice, and Societal Impact
TechnologyArtificial General Intelligence (AGI)Deep LearningReinforcement LearningComputational Cognitive Science - lexfridman
MIT 6.S094: Introduction to Deep Learning, Neural Networks, and Self-Driving Cars
TechnologyDeep LearningDeep Neural NetworksSelf-Driving CarsDeep Reinforcement Learning - lexfridman
MIT 6.S094: Deep Learning for Self-Driving Cars - Foundations, Challenges, and Human-Centered AI
TechnologyDeep LearningSelf-Driving CarsArtificial Intelligence (AI)Reinforcement Learning - lexfridman
Oriol Vinyals on AlphaStar, Deep Reinforcement Learning, and the Evolution of AI in Real-Time Strategy Games
TechnologyDeep LearningReinforcement Learning (RL)AlphaStarStarCraft (Real-Time Strategy game) - lexfridman
Programming Meme Review with George Hotz: Automation, AI, and the Culture of Code
TechnologyProgramming memesAutomation paradoxSelf-driving carsKnowledge outsourcing - lexfridman
MIT 6.S091 Introduction to Deep Reinforcement Learning: Fundamentals, Challenges, and Applications
TechnologyDeep Reinforcement Learning (Deep RL)Deep Neural NetworksSequential DecisionsTrial and Error - lexfridman
Andrew Ng on Deep Learning, Education, Automation, and the Future of AI Development
TechnologyMachine LearningDeep LearningArtificial Intelligence (AI)Automation - lexfridman
Practical Deep Learning Strategies: Scale, End-to-End Architectures, and Evolving Bias-Variance Trade-offs
TechnologyDeep Learning ProgressScale (Data & Computation)Traditional Learning AlgorithmsNeural Networks
Knowledge Graph
Related concepts — line thickness indicates connection strength. Click any node to explore.
Want to explore how this connects to concepts you choose? Try Nexus →