Related papers: SKILL-IL: Disentangling Skill and Knowledge in Mul…

The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that…

Efficient and robust policy transfer remains a key challenge for reinforcement learning to become viable for real-wold robotics. Policy transfer through warm initialization, imitation, or interacting over a large set of agents with…

For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is seldom possible to perfectly equip robots for economic…

It is crucial that users are empowered to take advantage of the functionality of a robot and use their understanding of that functionality to perform novel and creative tasks. Given a robot trained with Reinforcement Learning (RL), a user…

We present an algorithm that learns to imitate expert behavior and can transfer to previously unseen domains without retraining. Such an algorithm is extremely relevant in real-world applications such as robotic learning because 1) reward…

Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL). While recent works have attempted to understand the…

Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to…

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However,…

In multi-task reinforcement learning, it is possible to improve the data efficiency of training agents by transferring knowledge from other different but related tasks. Because the experiences from different tasks are usually biased toward…

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelihood given the demonstrations. Yet, human demonstrations are…

Automating the segregation process is a need for every sector experiencing a high volume of materials handling, repetitive and exhaustive operations, in addition to risky exposures. Learning automated pick-and-place operations can be…

We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption that learning from different tasks, sharing common properties,…

Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a…

We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for visual navigation into…

We consider task allocation for multi-object transport using a multi-robot system, in which each robot selects one object among multiple objects with different and unknown weights. The existing centralized methods assume the number of…

Long-Horizon (LH) tasks in Human-Scene Interaction (HSI) are complex multi-step tasks that require continuous planning, sequential decision-making, and extended execution across domains to achieve the final goal. However, existing methods…

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly…

Spatial reasoning over text is challenging as the models not only need to extract the direct spatial information from the text but also reason over those and infer implicit spatial relations. Recent studies highlight the struggles even…

Recent advances in machine learning have made it possible to train artificially intelligent agents that perform with super-human accuracy on a great diversity of complex tasks. However, the process of training these capabilities often…