Think Deep and Fast: Learning Neural Nonlinear Opinion Dynamics from Inverse Dynamic Games for Split-Second Interactions
Non-cooperative interactions commonly occur in multi-agent scenarios such as car racing,
where an ego vehicle can choose to overtake the rival, or stay behind it until a safe …
where an ego vehicle can choose to overtake the rival, or stay behind it until a safe …
Opinion-guided games: Strategic coordination through gradient-based opinion dynamics
K Nakamura - 2023 - dataspace.princeton.edu
As the performance capabilities of autonomous agents continue to increase, being able to
effectively coordinate with other agents becomes vital for deployment in real-world …
effectively coordinate with other agents becomes vital for deployment in real-world …
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
The accurate modeling of dynamics in interactive environments is critical for successful long-
range prediction. Such a capability could advance Reinforcement Learning (RL) and …
range prediction. Such a capability could advance Reinforcement Learning (RL) and …
Blending data-driven priors in dynamic games
As intelligent robots like autonomous vehicles become increasingly deployed in the
presence of people, the extent to which these systems should leverage model-based game …
presence of people, the extent to which these systems should leverage model-based game …
Decoupled Actor-Critic
M Nauman, M Cygan - arXiv preprint arXiv:2310.19527, 2023 - arxiv.org
Actor-Critic methods are in a stalemate of two seemingly irreconcilable problems. Firstly,
critic proneness towards overestimation requires sampling temporal-difference targets from …
critic proneness towards overestimation requires sampling temporal-difference targets from …
Inferring Occluded Agent Behavior in Dynamic Games with Noise-Corrupted Observations
T Qiu, D Fridovich-Keil - arXiv preprint arXiv:2303.09744, 2023 - arxiv.org
Robots and autonomous vehicles must rely on sensor observations, eg, from lidars and
cameras, to comprehend their environment and provide safe, efficient services. In multi …
cameras, to comprehend their environment and provide safe, efficient services. In multi …
Game-theoretic objective space planning
Autonomous Racing awards agents that react to opponents' behaviors with agile maneuvers
towards progressing along the track while penalizing both over-aggressive and over …
towards progressing along the track while penalizing both over-aggressive and over …
Learning temporal strategic relationships using generative adversarial imitation learning
This paper presents a novel framework for automatic learning of complex strategies in
human decision making. The task that we are interested in is to better facilitate long term …
human decision making. The task that we are interested in is to better facilitate long term …
Towards learning multi-agent negotiations via self-play
Y Tang - Proceedings of the IEEE/CVF International …, 2019 - openaccess.thecvf.com
Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent
systems. This is especially critical for planning in complex multi-agent environments, where …
systems. This is especially critical for planning in complex multi-agent environments, where …
Deep interactive motion prediction and planning: Playing games with motion prediction models
In most classical Autonomous Vehicle (AV) stacks, the prediction and planning layers are
separated, limiting the planner to react to predictions that are not informed by the planned …
separated, limiting the planner to react to predictions that are not informed by the planned …