CS885 - Semi-Markov Decision Processes
Explore semi-Markov decision processes, reinforcement learning, and queueing theory. Learn about Bellman's equation and the option framework for advanced decision-making strategies.
Trust Region Policy Optimization
Explore trust region policy optimization in reinforcement learning, covering key concepts like policy gradient, KL-penalized problems, and the TRPO algorithm.
Deep Recurrent Q-Networks
Explore deep reinforcement learning with recurrent neural networks, focusing on LSTM units, Q-learning, and their applications in sequential decision-making problems.
Partially Observable RL
Explore partially observable reinforcement learning, covering Markov decision processes, hidden Markov models, and belief monitoring in this comprehensive lecture.
Hidden Markov Models
Learn about Hidden Markov Models, their applications in speech recognition and robotics, and key algorithms like the Forward Algorithm in this comprehensive overview.
Bayesian RL
Explore Bayesian reinforcement learning techniques, including planning, sampling, and value iteration, to optimize decision-making in uncertain environments.
Model-Based RL
Explore model-based reinforcement learning, including complex models, Dyna algorithm, search trees, and Monte Carlo methods for effective planning and decision-making.
Bayesian and Contextual Bandits
Explore Bayesian and contextual bandits, covering multi-armed bandits, Bayesian learning, Thompson sampling, and contextual applications in this comprehensive lecture.
CS885: Multi-Armed Bandits
Explore multi-armed bandits, stochastic bandits, and online optimization strategies. Learn about exploration-exploitation trade-offs, regret, and epsilon-greedy approaches in practical applications.
Actor Critic
Learn about actor-critic methods in reinforcement learning, covering REINFORCE, temporal difference updates, and deterministic policy gradients for continuous action spaces.
Policy Gradient
Learn about policy gradient methods in reinforcement learning, covering stochastic policies, supervised learning, and the stochastic gradient policy theorem with applications to AlphaGo.
Deep Q-Networks
Learn advanced reinforcement learning techniques, focusing on Deep Q-Networks. Explore approximation, optimization, and practical implementations to enhance AI decision-making capabilities.
OpenAI Environments - Mike Rudd
Explore OpenAI environments, including robotics and retro games. Learn to build custom environments and understand reinforcement learning concepts like reward functions.
Conversational Agents
Explore intent classification, named entity recognition, and neural text generation in dialogue systems, focusing on challenges and advancements in conversational AI.
Markov Decision Processes
Explore Markov Decision Processes, their components, and applications in inventory management. Learn about rewards, discounting, and Bellman's equation for optimal decision-making.
Partially Observable Reinforcement Learning
Explore partially observable reinforcement learning, covering Markov processes, hidden models, and recurrent neural networks for decision-making in uncertain environments.
Normalizing Flows - Priyank Jaini
Explore normalizing flows, density estimation, and autoregressive models. Learn about change of variables, increasing triangular maps, and neural autoregressive flows.
Inverse RL
Explore inverse reinforcement learning, its applications, and key concepts like feature matching and maximizing margins. Learn implementation techniques and policy induction.
Distributional RL
Explore distributional reinforcement learning, covering return distribution, policy evaluation, and the C51 algorithm, with insights into its advantages and applications in Atari games.
Imitation Learning
Explore imitation learning techniques, from behavioral cloning to generative adversarial methods, with applications in autonomous driving and conversational agents.
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.