Maximum Entropy Reinforcement Learning
Explore maximum entropy reinforcement learning, covering key concepts like soft Q-learning and soft actor-critic algorithms, with a focus on encouraging stochasticity in optimal policies.
Trust Region & Proximal Policy Optimization
Explore trust region methods and proximal policy optimization in reinforcement learning, focusing on policy gradients, KL divergence, and practical implementations like TRPO and PPO.
Introduction to RL
Learn key concepts of reinforcement learning including Markov decision processes, policy optimization, and model-free evaluation through lectures and examples like the inverted pendulum and toy maze.
Policy Iteration
Learn about policy iteration in reinforcement learning, covering optimization, monotonic improvement, convergence, and complexity analysis.
Better Learning from the Past - Counterfactual - Batch RL
Explore counterfactual and batch reinforcement learning for improved decision-making under uncertainty, with focus on generalization bounds and policy optimization techniques.
Reinforcement Learning via an Optimization Lens
Explore reinforcement learning through an optimization lens, covering MDPs, Bellman equations, and novel approaches to solving RL problems using linear programming and primal-dual formulations.
Reinforcement Learning in Recommender Systems - Some Challenges
Explore challenges in applying reinforcement learning to recommender systems, including scale, stochastic action sets, and user learning over long horizons. Gain insights on addressing these issues.
Off-Policy Policy Optimization
Explore advanced reinforcement learning techniques, focusing on off-policy optimization, batch methods, and sequential decision-making in deep learning contexts.
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes
Explore policy gradient methods in Markov Decision Processes, covering optimality, approximation, and key concepts like entropy regularization and natural policy gradient.
On the Hardness of Reinforcement Learning With Value-Function Approximation
Explore challenges in reinforcement learning with value-function approximation, focusing on batch learning in large MDPs and the limitations of realizability assumptions.
Reinforcement Learning in Feature Space: Complexity and Regret
Explore reinforcement learning in feature space, focusing on complexity, regret analysis, and innovative approaches like MatrixRL. Learn about state feature mapping and its applications in real-world scenarios.
Alternatives to Reinforcement Learning for Real-World Problems
Explore alternatives to Reinforcement Learning for real-world problems, focusing on Contextual Bandits and Imitation Learning. Learn their applications, limitations, and how they differ from full RL.
How to Train Your Robot - An Introduction to Reinforcement Learning
Explore reinforcement learning for robotics, covering key concepts, workflow, and practical applications. Learn to define environments, create agents, and deploy policies to hardware platforms.
An Intuition-Based Approach to Reinforcement Learning
Explore an intuition-based approach to reinforcement learning, covering key concepts like exploit vs. explore, Q-tables, and stochastic actions, with practical examples and applications.
KDD 2020- Learning by Exploration-Part 2
Explore advanced techniques in online learning, including graph Laplacian regularization, social influence modeling, adaptive clustering, and particle Thompson sampling for improved exploration and personalization.
Multi-Agent Reinforcement Learning - Part II
Explore advanced concepts in multi-agent reinforcement learning, including equilibrium, rewards, and techniques like Q-value and no-regret learning. Gain insights into challenges and applications in AI and game theory.
Reinforcement Learning - Part I
Explore reinforcement learning fundamentals, including credit assignment, dynamic programming, and exploration algorithms. Gain insights into algorithm design and sample complexity in this comprehensive introduction.
Equivariant RL
Explore equivariant reinforcement learning, its advantages, and applications in graph neural networks with Max Welling from the University of Amsterdam.
Offline Reinforcement Learning and Model-Based Optimization
Explore offline reinforcement learning and model-based optimization techniques, focusing on data-driven approaches, Q-function lower bounds, and model inversion networks for automated decision-making.
Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning
Explore instance-dependent optimality in reinforcement learning, focusing on policy evaluation and TD learning. Gain insights into achieving optimal algorithms and useful bounds.
What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation?
Explore statistical limitations in offline reinforcement learning with function approximation, covering realizability, coverage, policy evaluation, and practical considerations.