7 citations · 14 across the 13 of their papers we have counts for
18 papers
Projected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets
Shripad V. Deshmukh, Christian Bock, Kangrui Ruan +4
On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilities. On hard problems, however,…
ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs
Yi Ge, Kangrui Ruan, Jifan Chen +6
Rapid advances in large language models have made software engineering agents capable of tackling complex coding tasks. Within a containerized environment, a coding agent receives…
Reward-Aligned Distillation
Yilan Chen, Zian Su, Manish Prajapat +4
Reinforcement learning with verifiable rewards improves the reasoning capabilities of large language models, but remains computationally expensive and sample inefficient. On-policy…
Sampling-Based Safe Reinforcement Learning
Luca Vignola, Bruce D. Lee, Manish Prajapat +4
Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcemen…
Goal-oriented safe active learning for predictive control using Bayesian recurrent neural networks
Laura Boca de Giuli, Alessio La Bella, Manish Prajapat +4
A key challenge in learning-based model predictive control (MPC) is to collect informative data online for model adaptation while ensuring safety and without penalising control per…
Safe Exploration via Policy Priors
Manuel Wendl, Yarden As, Manish Prajapat +3
Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle thi…
Safe and Near-Optimal Control with Online Dynamics Learning
Manish Prajapat, Johannes Köhler, Melanie N. Zeilinger +1
Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe…
Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery
Yunke Ao, Manish Prajapat, Yarden As +6
Safety-critical control using high-dimensional sensory feedback from optical data (e.g., images, point clouds) poses significant challenges in domains like autonomous driving and r…
SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
Yunke Ao, Masoud Moghani, Mayank Mittal +6
Ultrasound (US) is a widely used medical imaging modality due to its real-time capabilities, non-invasive nature, and cost-effectiveness. Robotic ultrasound can further enhance its…
Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics
Manish Prajapat, Johannes Köhler, Amon Lahr +2
Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However…
Performance-driven Constrained Optimal Auto-Tuner for MPC
Albert Gassol Puigjaner, Manish Prajapat, Andrea Carron +2
A key challenge in tuning Model Predictive Control (MPC) cost function parameters is to ensure that the system performance stays consistently above a certain threshold. To address…
Stochastic Model Predictive Control for Sub-Gaussian Noise
Yunke Ao, Johannes Köhler, Manish Prajapat +4
We propose a stochastic Model Predictive Control (MPC) framework that ensures closed-loop chance constraint satisfaction for linear systems with general sub-Gaussian process and me…
SMART: Self-learning Meta-strategy Agent for Reasoning Tasks
Rongxing Liu, Kumar Shridhar, Manish Prajapat +2
Tasks requiring deductive reasoning, especially those involving multiple steps, often demand adaptive strategies such as intermediate generation of rationales or programs, as no si…
Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming framework
Manish Prajapat, Amon Lahr, Johannes Köhler +2
Learning uncertain dynamics models using Gaussian process~(GP) regression has been demonstrated to enable high-performance and safety-aware control strategies for challenging real-…
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
Riccardo De Santi, Manish Prajapat, Andreas Krause
In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model…
Safe Guaranteed Exploration for Non-linear Systems
Manish Prajapat, Johannes Köhler, Matteo Turchetta +2
Safely exploring environments with a-priori unknown constraints is a fundamental challenge that restricts the autonomy of robots. While safety is paramount, guarantees on sufficien…
Submodular Reinforcement Learning
Manish Prajapat, Mojmír Mutný, Melanie N. Zeilinger +1
In reinforcement learning (RL), rewards of states are typically considered additive, and following the Markov assumption, they are of states visited previous…
Near-Optimal Multi-Agent Learning for Safe Coverage Control
Manish Prajapat, Matteo Turchetta, Melanie N. Zeilinger +1
In multi-agent coverage control problems, agents navigate their environment to reach locations that maximize the coverage of some density. In practice, the density is rarely known…