Collaborative training of heterogeneous reinforcement learning agents in environments with sparse rewards: what and when to share?

Computer Science

• Reinforcement Learning 100%
• Learning Agent 100%
• Intrinsic Motivation 100%
• Learning Process 66%
• Knowledge-Sharing 33%
• Transfer Learning 33%
• Learning Framework 33%
• Full State Space 33%
• Independent Learning 33%
• Model Architecture 33%
• multi agent 33%
• Computational Cost 33%
• Collaborative Learning 33%