This problem setting is motivated by the successful deep Q-networks (DQN) framework that falls in this regime.

Our method efficiently infers the trial-to-trial changes inananimal'spolicy,and decomposes those changes into a learning component and a noise component.

The understanding of such failure cases is still limited. For instance, the training process of reinforcement learning is unstable and the learning curve can fluctuate during training in ways that are hard to predict. The probability of obtaining satisfactory policies can also be inherently low in reward-sparse or highly nonlinear control tasks.