Reinforcement Learning (English): Master the Art of RL

سرفصل های دوره

Reinforcement Learning

1. Introduction

1. Course introduction

2. Course overview

2. Introduction to Reinforcement Learning

1. Module intro and roadmap

2. What is RL

3. What RL can do

4. The RL problem setup (AREA)

5. Reward

6. RL vs. Supervised Learning

7. State

8. AREA examples and quizes

9. Gym Environments

10. Inside RL agent - RL agent ingredients

11. Policy

12. Value

13. Model

14. RL agents taxonomy

15. Prediction vs Control

3. Markov Decision Process (MDP)

1. Module intro and roadmap

2. Markov Chain and Markov Process (MP)

3. Markov Reward Process (MRP)

4. Markov Decision Process (MDP)

5. Prediction

6. Bellman Equations with action-value function Q

7. Control

4. MDP solutions spaces

1. Module intro and roadmap

2. Planning with Dynamic Programming (DP)

3. Prediction with DP - Policy Evaluation

4. Control with DP - Policy Iteration and Value Iteration

5. Value Iteration example

6. Prediction with Monte-Carlo - MC Policy Evaluation

7. Prediction with Temporal-Difference (TD)

8. TD Lambda

9. Control with Monte-Carlo - MC Policy Iteration

10. Control with TD - SARSA

11. On-policy vs. Off-policy

12. Q-learning

13. MDP solutions summary

5. Deep Reinforcement Learning (DRL)

1. Module intro and roadmap

2. Large Scale Reinforcement Learning

3. DNN as function approximator

4. Value Function Approximation

5. DNN policies

6. Value function approximation with DL encoder-decoder pattern

7. Deep Q-Networks (DQN)

8. DQN Atari Example with Keras-RL and TF-Agents

6. Advanced DRL

1. Module intro and roadmap

2. Value-based vs Policy based vs Actor-Critic

3. Policy Gradients (PG)

4. REINFORCE - Monte-Carlo PG

5. AC - Actor-Critic

6. A2C - Advantage Actor-Critic

7. A3C - Asynchronous Advantage Actor-Critic

8. TRPO - Trusted Region Policy Optimization

9. PPO - Proximal Policy Optimization

10. DDPG - Deep Determinstic Policy Gradients

11. StableBaselines library overview

12. Atari example with stable-baselines

13. Mario example with stable-baselines

14. StreetFighter example with stable-baselines

7. Model-based Reinforcement Learning

1. Module intro and roadmap

2. Model learning methods

3. Model learning with Supervised Learning and Function Approximation

4. Sample based planning

5. Dyna - Intergation planning and Learning

8. Conclusion

1. Conclusion

9. Material

1. Slides.html

139,000 تومان

خرید اشتراک افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy-Training