Latent exploration for Reinforcement Learning (Lattice)
Lattice injects exploration noise into the latent state of the policy network, inducing structured exploration across action elements.
Nov 3, 2023
MyoChallenge 2022: Learning contact-rich manipulation using a musculoskeletal hand
Jan 1, 2023
DMAP: a Distributed Morphological Attention Policy for learning to locomote with a changing body
DMAP is an attention-based policy network which develops a representation of the agent's body and adapts to its changes.
Nov 1, 2022
Out-of-distribution generalization of internal models is correlated with reward
Jan 1, 2021