A Sharp Analysis of Model-based Reinforcement Learning with Self-Play

Computer Science

• Reinforcement Learning 100%
• Model-Based Reinforcement Learning 100%
• Efficient Algorithm 50%
• Markov Decision Process 50%
• multi agent 50%
• Multi-Agent Reinforcement Learning 50%
• Game Playing 50%
• Learning Practice 50%
• Optimistic Algorithm 50%

Keyphrases

• Markov Policy 66%
• Non-Markov 33%