Anurag Koul

Learning Finite State Representations of Recurrent Policy Networks

2018 · arXiv (Cornell University)

Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems. RNN policies, however, are particularly difficult to explain, understand, and analyze due to their …

PcLast: Discovering Plannable Continuous Latent States

2023 · arXiv (Cornell University)

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision making, they ignore state reachability, hampering their performance. In this …