Lectures related to Temporal difference learning

Continuous Reinforcement Learning: Advanced Machine Learning

Explores continuous-state reinforcement learning challenges, value function estimation, policy gradients, and Policy learning by Weighted Exploration.

N-step TD Methods: SARSA and Expected SARSA

Explores n-step TD methods in reinforcement learning, improving information flow and estimation accuracy.

Reinforcement Learning: Policy Gradient and Actor-Critic Methods

Provides an overview of reinforcement learning, focusing on policy gradient and actor-critic methods for deep artificial neural networks.

Long-Horizon Robot Exploration Strategies

Explores strategies for long-horizon robot exploration in continuous action spaces for multi-object search.

Risk Minimization from Adaptively Collected Data

Explores risk minimization from adaptively collected data with guarantees for policy learning and the importance of exploration strategies.

TD Learning: Temporal Difference Learning

Covers Temporal Difference Learning, V-values, state-values, and TD methods in reinforcement learning.

Temporal difference learning

Covers Reinforcement Learning theory, Q-Learning, and multi-step horizons.

Exploration and exploitation

Covers the theory of Reinforcement Learning, focusing on the Exploration/Exploitation dilemma and strategies to balance exploration and exploitation.

Reinforcement Learning: Eligibility Traces

Explores Reinforcement Learning, focusing on updating previous action values along the trajectory using the SARSA algorithm.

Reinforcement Learning: Q-Learning

Covers Q-Learning, a model-free reinforcement learning algorithm, and its application to Tic-Tac-Toe with examples and quizzes.

Policy Gradient and Actor-Critic Methods: Eligibility Traces Explained

Discusses policy gradient and actor-critic methods, focusing on eligibility traces and their application in reinforcement learning tasks.

Actor-Critic Architecture and Advantage-Actor-Critic

Explores actor-critic networks and the advantage actor critic method for optimizing parameters to maximize return.

Reinforcement Learning: SARSA Algorithm

Explores the SARSA algorithm for reinforcement learning, focusing on updating Q-values and the importance of exploration in learning by rewards.

Modeling the input space

Explores modeling continuous input spaces in reinforcement learning using neural networks and radial basis functions.

Reinforcement Learning: TD Learning and SARSA Variants

Discusses reinforcement learning, focusing on temporal difference learning and SARSA algorithm variations.

Safe Learning and Control

Explores safe learning, control, multi-agent coordination, and Nash equilibrium convergence in intelligent systems.

Theory of reinforcement learning: Introductory question

Covers the theory of reinforcement learning, exploring exploration/exploitation dilemma and continuous state/action spaces.

Reinforcement Learning: BackUp Diagrams

Introduces the BackUp diagram as a key graphic representation in reinforcement learning.

Elements of Reinforcement Learning

Introduces the fundamental elements of Reinforcement Learning and demonstrates their application with the Acrobot system.

Reinforcement Learning: Q-Learning

Covers Q-Learning in reinforcement learning, exploring action values, policies, and the societal impact of algorithms.