Please enable JavaScript.
Coggle requires JavaScript to display documents.
Reinforcement Learning (Key Concepts (Taxonomy of RL Algorithms,…
Reinforcement Learning
Key Concepts
Taxonomy of RL Algorithms
Challenges of RL for Robotics
Natural vs Vanilla Gradients
Variance in Returns
Target Networks
Replay Buffers
Constrained Policy Updates
Model Free Algorithms
Policy Gradients
Success Matching
Value Functions
Stochastic Search Methods
Model Based Algorithms
Analytic Policy Gradients
Trajectory Optimization
Model Free + Simulation
Exploration
Policy Exploration
Parameter Exploration
Step Based Exploration
Active Learning
Safe Exploration
Optimistic Exploration
Policy Representations
Via Points and Splines
Motor Primitives
Gaussian Mixture Models
Neural Networks
Controllers
Non-parametric