Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations

Understand

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents.

• In many real-world applications, the agents can only acquire a partial view of the world.
• Here we consider a setting whereby most agents' observations are also extremely noisy, hence only weakly correlated to the true state of the environment.
• Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations.