Policy Advisory Module for Exploration Hindrance Problem in Multi-agent Deep Reinforcement Learning

Mathematics

• Multiagent Learning 100%
• Reinforcement Learning 72%
• Policy 47%
• Module 32%
• Disaster 23%
• Collision 16%
• Performance 14%
• Entire 13%
• Testing 11%
• Multi-agent Systems 10%
• Reward 9%
• Experimental Results 8%
• Likely 7%
• Scenarios 7%
• Context 4%

Engineering & Materials Science

• Reinforcement learning 48%
• Disasters 15%
• Testing 8%
• Multi agent systems 7%
• Deep learning 7%