JHJarrett Holtz

Jarrett Holtz

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jarrett Holtz has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions

    by Laszlo Szoke, Shahaf S. Shperberg, Jarrett Holtz, Alessandro Allievi

    This work addresses the challenge of reinforcement learning with reward functions that feature highly imbalanced components in terms of importance and scale. Reinforcement learning algorithms generally struggle to handle such imbalanced reward functions effectively. Consequently, they often converge to suboptimal policies that favor only the dominant reward component. For example, agents might adopt passive strategies, avoiding any action to evade potentially unsafe outcomes entirely. To mitigate the adverse effects of imbalanced reward functions, we introduce a curriculum learning approach based on the successor features representation. This novel approach enables our learning system to acquire policies that take into account all reward components, allowing for a more balanced and versatile decision-making process.


  • Programmatic Imitation Learning From Unlabeled and Noisy Demonstrations

    by Jimmy Xin, Linus Zheng, Kia Rahmani, Jiayi Wei, Jarrett Holtz, Isil Dillig, Joydeep Biswas

    Imitation Learning (IL) is a promising paradigm for teaching robots to perform novel tasks using demonstrations. Most existing approaches for IL utilize neural networks (NN), however, these methods suffer from several well-known limitations: they 1) require large amounts of training data, 2) are hard to interpret, and 3) are hard to refine and adapt. There is an emerging interest in Programmatic Imitation Learning (PIL), which offers significant promise in addressing the above limitations. In PIL, the learned policy is represented in a programming language, making it amenable to interpretation and adaptation to novel settings. However, state-of-the-art PIL algorithms assume access to action labels and struggle to learn from noisy real-world demonstrations. In this paper, we propose PLUNDER, a novel PIL algorithm that addresses these shortcomings by synthesizing probabilistic programmatic policies that are particularly well-suited for modeling the uncertainties inherent in real-world demonstrations. Our approach leverages an EM loop to simultaneously infer the missing action labels and the most likely probabilistic policy. We benchmark PLUNDER against several established IL techniques, and demonstrate its superiority across five challenging imitation learning tasks under noise. PLUNDER policies outperform the next-best baseline by 19% and 17% in matching the given demonstrations and successfully completing the tasks, respectively.


  • Open Access

    SocialGym: A Framework for Benchmarking Social Robot Navigation

    by Jarrett Holtz, Joydeep Biswas

    Robots moving safely and in a socially compliant manner in dynamic human environments is an essential benchmark for long-term robot autonomy. However, it is not feasible to learn and benchmark social navigation behaviors entirely in the real world, as learning is data-intensive, and it is challenging to make safety guarantees during training. Therefore, simulation-based benchmarks that provide abstractions for social navigation are required. A framework for these benchmarks would need to support a wide variety of learning approaches, be extensible to the broad range of social navigation scenarios, and abstract away the perception problem to focus on social navigation explicitly. While there have been many proposed solutions, including high fidelity 3D simulators and grid world approximations, no existing solution satisfies all of the aforementioned properties for learning and evaluating social navigation behaviors. In this work, we propose SocialGym, a lightweight 2D simulation environment for robot social navigation designed with extensibility in mind, and a benchmark scenario built on SocialGym. Further, we present benchmark results that compare and contrast human-engineered and model-based learning approaches to a suite of off-the-shelf Learning from Demonstration (LfD) and Reinforcement Learning (RL) approaches applied to social robot navigation. These results demonstrate the data efficiency, task performance, social compliance, and environment transfer capabilities for each of the policies evaluated to provide a solid grounding for future social navigation research.