Yu Fan Chen

TL;DR: This work extends the previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules, and introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size.

TL;DR: This work develops an algorithm that learns collision avoidance among a variety of heterogeneous, non-communicating, dynamic agents without assuming they follow any particular behavior rules and extends the previous work by introducing a strategy using Long Short-Term Memory (LSTM) that enables the algorithm to use observations of an arbitrary number of other agents.

TL;DR: In this article, an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules is presented. But this algorithm is implemented using key assumptions about other agents' behavior that deviate from reality as the number of agents in the environment increases.

TL;DR: In this paper, a distributed learning framework for multi-agent sequential decision-making under uncertainty and incomplete knowledge of the state transition model is proposed, where each agent learns an individual model and shares the results with the team, and the model sharing problem is addressed by having each agent rank the features of their representation based on the model reduction error and broadcast the most relevant features to their teammates.

TL;DR: The proposed distributed learning framework, where each agent learns an individual model and shares the results with the team, is proposed and can outperform planners that do not account for heterogeneity between agents.