Completed
Policy Iteration (PI) Algorithm
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Multiagent Reinforcement Learning: Rollout and Policy Iteration
Automatically move to the next video in the Classroom when playback concludes
- 1 Sources
- 2 Multiagent Problems - A Very Old (19608) and Well-Researched Field
- 3 For this Talk we Focus on Finite-State Intinite Horizon Problems
- 4 Policy Iteration (PI) Algorithm
- 5 Outline of Our Approach for Multiagent Problems
- 6 Underlying Theory: Trading off Control and State Complexity (NDP book, 1996)
- 7 Comparing Standard with Multiagent Rollout/Policy Iteration
- 8 Approximate Policy Iteration with Agent-by-Agent Policy Improvement
- 9 Concluding Remarks
