7 citations · 14 across the 13 of their papers we have counts for
9 papers · 1 filter
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…
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…
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…
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…
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…