Active hypothesis testing in unknown environments using recurrent neural networks and model free reinforcement learning
This addresses the challenge of hypothesis testing in unknown environments for applications like robotics or decision-making, though it is incremental as it builds on existing RL and supervised learning techniques.
The paper tackled the problem of active sequential hypothesis testing in unknown environments without assumptions about priors, actions, observations, or dynamics, using a combination of deep reinforcement learning and supervised learning. The result is a method that performs competitively or better than the Chernoff test in finite and infinite horizon problems, even with continuous observations or actions.
A combination of deep reinforcement learning and supervised learning is proposed for the problem of active sequential hypothesis testing in completely unknown environments. We make no assumptions about the prior probability, the action and observation sets, and the observation generating process. Our method can be used in any environment even if it has continuous observations or actions, and performs competitively and sometimes better than the Chernoff test, in both finite and infinite horizon problems, despite not having access to the environment dynamics.