Related papers: Markov Balance Satisfaction Improves Performance i…

The field of robotic manipulation has advanced significantly in recent years. At the sensing level, several novel tactile sensors have been developed, capable of providing accurate contact information. On a methodological level, learning…

Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort…

Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? These scenarios force us to evaluate the trade-off between collective rules…

Self-imitation learning is a Reinforcement Learning (RL) method that encourages actions whose returns were higher than expected, which helps in hard exploration and sparse reward problems. It was shown to improve the performance of…

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…

Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observation spaces prevalent in robotics. This paper addresses the…

Imitation learning (IL) has shown great success in learning complex robot manipulation tasks. However, there remains a need for practical safety methods to justify widespread deployment. In particular, it is important to certify that a…

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Markov processes serve as a universal model for many real-world random processes. This paper presents a data-driven approach for learning these models through the spectral decomposition of the infinitesimal generator (IG) of the Markov…

Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL). ICL is efficient as it does not require any parameter updates to the trained LLM, but only few annotated examples as input for the LLM. In this work, we…

Online imitation learning (IL) is an algorithmic framework that leverages interactions with expert policies for efficient policy optimization. Here policies are optimized by performing online learning on a sequence of loss functions that…

In many real-world settings, an agent must learn to act in environments where no reward signal can be specified, but a set of expert demonstrations is available. Imitation learning (IL) is a popular framework for learning policies from such…

Existing communication methods for multi-agent reinforcement learning (MARL) in cooperative multi-robot problems are almost exclusively task-specific, training new communication strategies for each unique task. We address this inefficiency…

Contact-rich tasks continue to present many challenges for robotic manipulation. In this work, we leverage a multimodal visuotactile sensor within the framework of imitation learning (IL) to perform contact-rich tasks that involve relative…

We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-the-art adversarial methods which require updating the…

We consider the problem of Imitation Learning (IL) by actively querying noisy expert for feedback. While imitation learning has been empirically successful, much of prior work assumes access to noiseless expert feedback which is not…

Approaches based on generative adversarial networks for imitation learning are promising because they are sample efficient in terms of expert demonstrations. However, training a generator requires many interactions with the actual…

We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Our models…

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating simple binary…

Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when…