44 citations · 46 across the 8 of their papers we have counts for
9 papers
SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations
Peter Crowley, Zachary Serlin, Tyler Paine +3
Inverse Reinforcement Learning (IRL) presents a powerful paradigm for learning complex robotic tasks from human demonstrations. However, most approaches make the assumption that ex…
Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards
Ahmad Ahmad, Mehdi Kermanshah, Kevin Leahy +6
In this paper, we tackle the challenging problem of delayed rewards in reinforcement learning (RL). While Proximal Policy Optimization (PPO) has emerged as a leading Policy Gradien…
Comp-LTL: Temporal Logic Planning via Zero-Shot Policy Composition
Taylor Bergeron, Zachary Serlin, Kevin Leahy
This work develops a zero-shot mechanism, Comp-LTL, for an agent to satisfy a Linear Temporal Logic (LTL) specification given existing task primitives trained via reinforcement lea…
Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning
Kevin Leahy, Makai Mann, Zachary Serlin
Compositionality is a critical aspect of scalable system design. Reinforcement learning (RL) has recently shown substantial success in task learning, but has only recently begun to…
CatlNet: Learning Communication and Coordination Policies from CaTL+ Specifications
Wenliang Liu, Kevin Leahy, Zachary Serlin +1
In this paper, we propose a learning-based framework to simultaneously learn the communication and distributed control policies for a heterogeneous multi-agent system (MAS) under c…
Robust Multi-Agent Coordination from CaTL+ Specifications
Wenliang Liu, Kevin Leahy, Zachary Serlin +1
We consider the problem of controlling a heterogeneous multi-agent system required to satisfy temporal logic requirements. Capability Temporal Logic (CaTL) was recently proposed to…
Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications
Mingyu Cai, Makai Mann, Zachary Serlin +2
This paper explores continuous-time control synthesis for target-driven navigation to satisfy complex high-level tasks expressed as linear temporal logic (LTL). We propose a model-…
Distributed and Consistent Multi-Image Feature Matching via QuickMatch
Zachary Serlin, Guang Yang, Brandon Sookraj +2
In this work we consider the multi-image object matching problem, extend a centralized solution of the problem to a distributed solution, and present an experimental application of…
Sampling-based Motion Planning via Control Barrier Functions
Guang Yang, Bee Vang, Zachary Serlin +2
Robot motion planning is central to real-world autonomous applications, such as self-driving cars, persistence surveillance, and robotic arm manipulation. One challenge in motion p…