ConceptAI & ML
State space
The set of all possible states that a stochastic process or system can occupy.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
6Each in their own terms, from the easiest level.
Pieter Abbeel
The set of all possible states in a problem.Steven Strogatz
Another term for phase space, representing the space of all possible states of the system.Brian Yu
The set of all states reachable from the initial state by any sequence of actions.Edsger W. Dijkstra
The set of all possible configurations or values that a system can be in.Emma Brunskill
The set of all possible configurations or statuses that a system can occupy.
Lectures that assume it
50The first 12 are shown.
- Deterministic State Laws & Conservation of Information
- Breadth-First Search (BFS)
- Multiparticle States II: Entangled States, Bell Basis & Non-Factorizable Wavefunctions
- Planning by Dynamic Programming — Policy & Value Iteration
- Value Function Approximation & Deep Q-Networks (DQN)
- Gambler's Ruin and Random Variables
- Lyapunov Analysis I
- Search with Other Agents: Minimax
- A* Search and Heuristics
- Me and My Markov Blanket
- Exploration and Exploitation
- The Story of Sync
Connections
65The lectures that define it or assume it, and the concepts next to it.
Concepts9
Show 3 moreShow fewer
Lectures56
- Uninformed Search
- MAE5790-1 Course introduction and overview
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- Reasoning About Programs
- Stochastic Processes I
- Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
Show 50 moreShow fewer
- Deterministic State Laws & Conservation of Information
- Breadth-First Search (BFS)
- Multiparticle States II: Entangled States, Bell Basis & Non-Factorizable Wavefunctions
- Planning by Dynamic Programming — Policy & Value Iteration
- Value Function Approximation & Deep Q-Networks (DQN)
- Gambler's Ruin and Random Variables
- Lyapunov Analysis I
- Search with Other Agents: Minimax
- A* Search and Heuristics
- Me and My Markov Blanket
- Exploration and Exploitation
- The Story of Sync
- Bioelectricity: A Bridge Between Physics and Cognition, by Way of Biology
- Exploration of fundamental concepts in deep reinforcement learning
- Constraint Satisfaction Problems (CSPs) Part 1/2
- An Interplay Between Programming and Mathematics
- Linearizing Around a Fixed Point
- Nonlinear Dynamics
- Dynamic Programming I
- Acrobots, Cart-poles, and Quadrotors I
- Policy Gradient Foundations: Trajectory Distributions & High-Dimensional State Spaces
- Options Markets
- Markov Decision Processes (MDPs) Part 2/2
- What is Complexity?
- Bioelectricity in Morphogenesis and Cognition
- States, Logic & Complex Vector Spaces
- The History and Unreasonable Effectiveness of Feedback Control
- The Deep Learning Revolution: The Sequel (Turing Award Lecture)
- Dynamic Programming III
- Constraint Satisfaction Problems (CSPs) Part 2/2
- Autonomous Linear Dynamical Systems in Electrical Engineering
- Trajectory Optimization I
- Trajectory Stabilization
- Simple Models of Walking
- Hybrid Trajectory Optimization
- Planning + Control Through Contact
- Stochastic dynamics
- Particle Filtering
- Feedback Motion Planning
- Fluctuation Relation at the Beat of a Current
- Controllability, Reachability, and Eigenvalue Placement
- Towards a Statistical Foundation for Reinforcement Learning
- Output feedback
- Reinforcement Learning Part 2/2
- The Physics of Communication
- Sampling-based (kinodynamic) motion planning
- Cognitive Architectures: GPS, SOAR, Subsumption & The Society of Mind
- Imitation Learning, Foundation Models, and Course Wrap-up
- Thoughts as Thinkers: Biology and Computer Science of Inspiration
- Advanced Topics and Course Summary