Auto-bidding in real-time auctions via Oracle Imitation Learning (OIL)
OIL combines operations reserach techniques and imitation learning to train an auto-bidding agent for leal-time auctions.
Dec 18, 2024
Acquiring musculoskeletal skills with curriculum-based reinforcement learning
Our winning solution to the NeurIPS MyoChallenge provides insights about motor control and muscle synergies during object manipulation.
Nov 19, 2024
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
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