Online reinforcement learning of state representation in recurrent network supported by the power of random feedback and biological constraints.

ABSTRACT: Representation of external and internal states in the brain plays a critical role in enabling suitable behavior. Recent studies suggest that state representation and state value can be simultaneously learned through Temporal-Difference-Reinforcement-Learning (TDRL) and Backpropagation-Through-Time (BPTT) in recurrent neural networks (RNNs) and their readout. However, neural implementation of such learning remains unclear as BPTT requires offline update using transported downstream weights, which is suggested to be biologically implausible. We demonstrate that simple online training of RNNs using TD reward prediction error and random feedback, without additional memory or eligibility trace, can still learn the structure of tasks with cue-reward delay and timing variability. This is because

SUBMITTER: Tsurumi T 

PROVIDER: S-EPMC12459954 | biostudies-literature | 2025 Sep

REPOSITORIES: biostudies-literature