6 accepted papers
Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We define plasticity loss as the network’s diminishing ability to make reliable progress under gradient descent updates in all output-space directi…
Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filter…
Common policy gradient methods rely on the maximization of a sequence of surrogate functions. In recent years, many such surrogate functions have been proposed, most without strong theoretical guarantees, leading to algorithms such as TRPO, PPO, or MPO. Rather than design yet another surrogate funct…
We study meta-learning in Markov Decision Processes (MDP) with linear transition models in the undiscounted episodic setting. Under a task sharedness metric based on model proximity we study task families characterized by a distribution over models specified by a bias term and a variance component.…
Some of the most relevant future applications of multi-agent systems like autonomous driving or factories as a service display mixed-motive scenarios, where agents might have conflicting goals. In these settings agents are likely to learn undesirable outcomes in terms of cooperation under independen…
Humans and robots are increasingly sharing their workspaces to benefit from the precision, endurance, and strength of machines and the universal capabilities of humans. Instead of performing time-consuming real experiments, computer simulations of humans could help to optimally orchestrate human and…