Paper accepted at ICLR!

Our Paper, Time-Efficient Reinforcement Learning with Stochastic Stateful Policies, was accepted at the International Conference on Learning Representations (ICLR) 2024! We introduce a novel training approach for stateful policies, decomposing them into a stochastic internal state kernel and a stateless policy jointly optimized using our stochastic stateful policy gradient. This method overcomes the drawbacks of Backpropagation Through Time (BPTT), providing a faster and simpler alternative, as demonstrated in evaluations on complex continuous control tasks such as humanoid locomotion.