← Anthony Roumi
Notes
Reinforcement Learning · Motion Learning · Mathematics
Deep Reinforcement Learning
Policy Gradient Methods
Gradient Estimators
Baselines
Actor-Critic Methods
Advantage Estimation
Advanced Policy Gradient Methods
Mathematical Machinery
Entropy
KL Divergence
Parameter Updates in Distribution Space
Taylor Expansion
Gradient
Hessian
Fisher Information
Importance Sampling
Central Limit Theorem
Trust Region Policy Optimization (TRPO)
Natural Gradient
Proximal Policy Optimization (PPO)
Adversarial Learning
Motion Representation & Tracking
Motion Learning Algorithms