Distributed entropy-regularized multi-agent reinforcement learning with policy consensus

Computer Science

• Algorithm Design 25%
• Distributed Algorithm 25%
• Function Approximation 25%
• Learning Performance 25%
• Learning Problem 25%
• Limiting Factor 25%
• Linear Function 25%
• Markov Decision Process 25%
• Mathematical Convergence 25%
• multi agent 50%
• Multi Agent Systems 25%
• Multi-Agent Reinforcement Learning 100%
• Regularization 25%
• Reinforcement Learning 50%
• Simulation Experiment 25%
• Stochastic Approximation 25%
• training algorithm 25%

Mathematics

• Approximation of Function 50%
• Extensive Simulation Experiment 50%
• Sample Efficiency 100%

Chemical Engineering

• Multi Agent Systems 25%
• Reinforcement Learning 100%
• Scalability 25%