11 citations · 28 across the 12 of their papers we have counts for
13 papers
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang +7
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing ben…
Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Elmira Amirloo, Jean-Philippe Fauconnier, Christoph Roesmann +8
Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains…
Simplified Temporal Consistency Reinforcement Learning
Yi Zhao, Wenshuai Zhao, Rinu Boney +2
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficienc…
SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations
Khaled Nakhleh, Minahil Raza, Mack Tang +6
We study the training performance of ROS local planners based on Reinforcement Learning (RL), and the trajectories they produce on real-world robots. We show that recent enhancemen…
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning
Yi Zhao, Rinu Boney, Alexander Ilin +2
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the qua…
Learning of feature points without additional supervision improves reinforcement learning from images
Rinu Boney, Alexander Ilin, Juho Kannala
In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using feature poin…
Learning to Play Imperfect-Information Games by Imitating an Oracle Planner
Rinu Boney, Alexander Ilin, Juho Kannala +1
We consider learning to play multiplayer imperfect-information games with simultaneous moves and large state-action spaces. Previous attempts to tackle such challenging games have…
RealAnt: An Open-Source Low-Cost Quadruped for Education and Research in Real-World Reinforcement Learning
Rinu Boney, Jussi Sainio, Mikko Kaivola +2
Current robot platforms available for research are either very expensive or unable to handle the abuse of exploratory controls in reinforcement learning. We develop RealAnt, a mini…
Learning to Drive (L2D) as a Low-Cost Benchmark for Real-World Reinforcement Learning
Ari Viitala, Rinu Boney, Yi Zhao +2
We present Learning to Drive (L2D), a low-cost benchmark for real-world reinforcement learning (RL). L2D involves a simple and reproducible experimental setup where an RL agent has…
Regularizing Model-Based Planning with Energy-Based Models
Rinu Boney, Juho Kannala, Alexander Ilin
Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional d…
Regularizing Trajectory Optimization with Denoising Autoencoders
Rinu Boney, Norman Di Palo, Mathias Berglund +4
Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting ina…
Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
Rinu Boney, Alexander Ilin
We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled exam…
Recurrent Ladder Networks
Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hotloo Hao +3
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recur…