Search Results for author:
Found 21 papers, 6 papers with code
Preference Optimization as Probabilistic Inference
Existing preference optimization methods are mainly designed for directly learning from human feedback with the assumption that paired examples (preferred vs. dis-preferred) are available.
Imitating Language via Scalable Inverse Reinforcement Learning
We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models.
Offline Actor-Critic Reinforcement Learning Scales to Large Models
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning.
Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments.
Dense RGB-D-Inertial SLAM with Map Deformations
While dense visual SLAM methods are capable of estimating dense reconstructions of the environment, they suffer from a lack of robustness in their tracking step, especially when the optimisation is poorly initialised.
The Challenges of Exploration for Offline Reinforcement Learning
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour.
Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
This causes BBE to be actively detrimental to policy learning in many control tasks.
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs.
Simple Sensor Intentions for Exploration
In particular, we show that a real robotic arm can learn to grasp and lift and solve a Ball-in-a-Cup task from scratch, when only raw sensor streams are used for both controller input and in the auxiliary reward definition.
Comparing View-Based and Map-Based Semantic Labelling in Real-Time SLAM
Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels.
Learning Meshes for Dense Visual SLAM
Estimating motion and surrounding geometry of a moving camera remains a challenging inference problem.
SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities.
MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM
It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene.
Matching Features without Descriptors: Implicitly Matched Interest Points
The extraction and matching of interest points is a prerequisite for many geometric computer vision problems.
Task-Embedded Control Networks for Few-Shot Imitation Learning
Despite this, most robot learning approaches have focused on learning a single task, from scratch, with a limited notion of generalisation, and no way of leveraging the knowledge to learn other tasks more efficiently.
LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo
In this paper, we propose LS-Net, a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.
Learning to Solve Nonlinear Least Squares for Monocular Stereo
In this paper, we propose a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.
Fusion++: Volumetric Object-Level SLAM
Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation.
CodeSLAM â Learning a Compact, Optimisable Representation for Dense Visual SLAM
Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.
CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM
Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.
gvnn: Neural Network Library for Geometric Computer Vision
We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning.
