Related papers: Plan-Space State Embeddings for Improved Reinforce…
Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for real-world applications. In order to reduce the data…
The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…
We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently…
Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert. These models can be used e.g. for system control by generalizing the expert demonstrations to previously…
Cross-robot policy learning -- training a single policy to perform well across multiple embodiments -- remains a central challenge in robot learning. Transformer-based policies, such as vision-language-action (VLA) models, are typically…
Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems…
Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learning from demonstration depends crucially on inductive bias in…
Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried…
Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventional method for…
Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…
Deep reinforcement learning produces robust locomotion policies for legged robots over challenging terrains. To date, few studies have leveraged model-based methods to combine these locomotion skills with the precise control of…
Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequential structure in reinforcement learning into the…
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 data. Learned dynamics models can be directly used for…
This paper investigates the generalisability of Koopman-based representations for chaotic dynamical systems, focusing on their transferability across prediction and control tasks. Using the Lorenz system as a testbed, we propose a…
Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL,…
In many machine learning tasks, learning a good representation of the data can be the key to building a well-performant solution. This is because most learning algorithms operate with the features in order to find models for the data. For…
Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating…
Solving robotic navigation tasks via reinforcement learning (RL) is challenging due to their sparse reward and long decision horizon nature. However, in many navigation tasks, high-level (HL) task representations, like a rough floor plan,…
Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning…
This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. The proposed solution builds upon a deep…