Topic
Reinforcement Learning
Reward-based learning, policy gradients, Q-learning, multi-agent systems, and real-world RL applications.
Fundamentals of Reinforcement Learning
Agent Exploration and Environment Interaction
Policy Gradient Methods
State Representation and Transitions
Maximization Bias in Q-Learning
Markov Decision Process Framework
Model-Based and Model-Free Control
Trust Region Policy Optimization
Reward Function Design
Policy Types and Optimal Policies
Actor-Critic Architectures
Maximum Entropy Reinforcement Learning
Experience Replay Buffer Mechanics
Target Network Stability
Discount Factor Dynamics
Exploration versus Exploitation Trade-off
Advanced Experience Replay Techniques
Value and Q-Function Estimation
Action Space Definitions
Bellman Equation Dynamics
Reinforcement Learning Optimization Parameters
Epsilon-Greedy Exploration Strategy
Catastrophic Forgetting in Deep RL
Temporal Credit Assignment Problem
Generalized Advantage Estimation
The Deadly Triad Instability
Partially Observable Markov Decision Processes
Episodic Task Characteristics