Charles Packer — accepted AI-conference papers

2022

Is Anyone There? Learning a Planner Contingent on Perceptual Uncertainty

Charles Packer, Nicholas Rhinehart, Rowan Thomas McAllister, Matthew A. Wright, Xin Wang, Jeff He +2

CoRL 2022poster

Robots in complex multi-agent environments should reason about the intentions of observed and currently unobserved agents. In this paper, we present a new learning-based method for prediction and planning in complex multi-agent environments where the states of the other agents are partially-observed…

Cited by 14 Source ↗Scholar ↗

2021

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Nicholas Rhinehart, Jeff He, Charles Packer, Matthew A. Wright, Rowan McAllister, Joseph E. Gonzalez +1

ICRA 2021poster

Humans have a remarkable ability to accurately reason about future events, including the behaviors and states of mind of other agents. Consider driving a car through a busy intersection: it is necessary to reason about the physics of the vehicle, the intentions of other drivers, and their beliefs ab…

Cited by 40 Source ↗code ↗Scholar ↗

2021

Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Charles Packer, Pieter Abbeel, Joseph E. Gonzalez

NeurIPS 2021poster

Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward environments. Although existing meta-RL algorithms can learn strategies…

Cited by 22 Source ↗PDF ↗Scholar ↗