Completed
Sample code for A2C
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Introduction to Reinforcement Learning - Distributed RL Systems - Lecture 9
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Today's Outline
- 3 System and architecture are the foundation
- 4 Properties of Distributed Systems
- 5 MIT EECS 6.824 Distributed Systems
- 6 Updating Model Parameters
- 7 Synchronous Update versus Asynchronous Update
- 8 Decentralized Asynchronous Stochastic Gradient Descend
- 9 Parallelism in Distributed ML Systems
- 10 Hogwild: Lock-free asynchronous SGD
- 11 Implementation of Hogwild (asych SGD) in PyTorch
- 12 Case Study: MapReduce
- 13 Case Study: DisBelief
- 14 Fun facts about Jeff Dean
- 15 Case Study: AlexNet
- 16 Diagram of Reinforcement Learning
- 17 Development of Distributed RL Systems
- 18 2013: Deep Q Network
- 19 2015: General Reinforcement Learning Architecture (GORILA)
- 20 Review on Actor-Critic Methods
- 21 A3C: Asynchronous Advantage Actor Critic (ABC)
- 22 Comparison to Variants of DQN and GORILA
- 23 Sample code for A3C
- 24 Why Asynchronism works in A3C?
- 25 Comparison of A3C and A2C
- 26 Sample code for A2C
- 27 2018: Apex-X (Distributed Prioritized Experience Replay)
- 28 2018: IMPALA (Importance Weighted Actor- Learner Architecture)
- 29 2018 RLlib: abstraction for distributed RL
- 30 Some Other Parallelizable Algorithms: (Revisited) Evolution Strategies
- 31 Case Study: Al for Modern Games
- 32 System Design for AlphaGo Zero
- 33 System Design for AlphaStar
- 34 Conclusion
