2.3k citations · 3.8k across the 166 of their papers we have counts for
27 papers · 1 filter
PantheonRL: A MARL Library for Dynamic Training Interactions
Bidipta Sarkar, Aditi Talati, Andy Shih +1
We present PantheonRL, a multiagent reinforcement learning software package for dynamic training interactions such as round-robin, adaptive, and ad-hoc training. Our package is des…
HyperSPNs: Compact and Expressive Probabilistic Circuits
Andy Shih, Dorsa Sadigh, Stefano Ermon
Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both ex…
LILA: Language-Informed Latent Actions
Siddharth Karamcheti, Megha Srivastava, Percy Liang +1
We introduce Language-Informed Latent Actions (LILA), a framework for learning natural language interfaces in the context of human-robot collaboration. LILA falls under the shared…
Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer
Suneel Belkhale, Ethan K. Gordon, Yuxiao Chen +3
Robot-assisted feeding in household environments is challenging because it requires robots to generate trajectories that effectively bring food items of varying shapes and sizes in…
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Nicholas Roy, Ingmar Posner, Tim Barfoot +17
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning metho…
Learning Feasibility to Imitate Demonstrators with Different Dynamics
Zhangjie Cao, Yilun Hao, Mengxi Li +1
The goal of learning from demonstrations is to learn a policy for an agent (imitator) by mimicking the behavior in the demonstrations. Prior works on learning from demonstrations a…
Open-domain clarification question generation without question examples
Julia White, Gabriel Poesia, Robert Hawkins +2
An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of u…
Learning Multimodal Rewards from Rankings
Vivek Myers, Erdem Bıyık, Nima Anari +1
Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimoda…
Influencing Towards Stable Multi-Agent Interactions
Woodrow Z. Wang, Andy Shih, Annie Xie +1
Learning in multi-agent environments is difficult due to the non-stationarity introduced by an opponent's or partner's changing behaviors. Instead of reactively adapting to the oth…
Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality
Songyuan Zhang, Zhangjie Cao, Dorsa Sadigh +1
Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data.…
Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams
Erdem Bıyık, Anusha Lalitha, Rajarshi Saha +2
When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of g…
Learning Reward Functions from Scale Feedback
Nils Wilde, Erdem Bıyık, Dorsa Sadigh +1
Today's robots are increasingly interacting with people and need to efficiently learn inexperienced user's preferences. A common framework is to iteratively query the user about wh…
APReL: A Library for Active Preference-based Reward Learning Algorithms
Erdem Bıyık, Aditi Talati, Dorsa Sadigh
Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algori…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic
Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh +2
With the adoption of autonomous vehicles on our roads, we will witness a mixed-autonomy environment where autonomous and human-driven vehicles must learn to co-exist by sharing the…
Learning Latent Actions to Control Assistive Robots
Dylan P. Losey, Hong Jun Jeon, Mengxi Li +5
Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use…
Cooperative Autonomous Vehicles that Sympathize with Human Drivers
Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh +2
Widespread adoption of autonomous vehicles will not become a reality until solutions are developed that enable these intelligent agents to co-exist with humans. This includes safel…
Social Coordination and Altruism in Autonomous Driving
Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh +2
Despite the advances in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehi…
Targeted Data Acquisition for Evolving Negotiation Agents
Minae Kwon, Siddharth Karamcheti, Mariano-Florentino Cuellar +1
Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the…
Emergent Prosociality in Multi-Agent Games Through Gifting
Woodrow Z. Wang, Mark Beliaev, Erdem Bıyık +3
Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of…
Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy
Erdem Bıyık, Daniel A. Lazar, Ramtin Pedarsani +1
Traffic congestion has large economic and social costs. The introduction of autonomous vehicles can potentially reduce this congestion by increasing road capacity via vehicle plato…
Learning Visually Guided Latent Actions for Assistive Teleoperation
Siddharth Karamcheti, Albert J. Zhai, Dylan P. Losey +1
It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functi…
On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Andy Shih, Arjun Sawhney, Jovana Kondic +2
Humans can quickly adapt to new partners in collaborative tasks (e.g. playing basketball), because they understand which fundamental skills of the task (e.g. how to dribble, how to…
Learning Human Objectives from Sequences of Physical Corrections
Mengxi Li, Alper Canberk, Dylan P. Losey +1
When personal, assistive, and interactive robots make mistakes, humans naturally and intuitively correct those mistakes through physical interaction. In simple situations, one corr…