Related papers: SIRL: Similarity-based Implicit Representation Lea…

Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms push the boundaries of…

Animals are able to imitate each others' behavior, despite their difference in biomechanics. In contrast, imitating the other similar robots is a much more challenging task in robotics. This problem is called cross domain imitation…

This paper addresses the problem of inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. IRL can provide a generalizable and compact representation for apprenticeship learning, and…

Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been proposed for learning representations that are invariant or…

Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult. However, despite the success of IL algorithms, they impose the somewhat unrealistic requirement that…

Model-based reinforcement learning (RL) algorithms designed for handling complex visual observations typically learn some sort of latent state representation, either explicitly or implicitly. Standard methods of this sort do not distinguish…

The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many pretext tasks lead…

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for…

How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations.…

A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive…

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational…

Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed automatically and efficiently from raw sensory inputs (such as…

Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior,…

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement…

Inverse reinforcement learning (IRL) is a common technique for inferring human preferences from data. Standard IRL techniques tend to assume that the human demonstrator is stationary, that is that their policy $\pi$ doesn't change over…

Imitation Learning (IL) is an effective learning paradigm exploiting the interactions between agents and environments. It does not require explicit reward signals and instead tries to recover desired policies using expert demonstrations. In…

Causal representation learning (CRL) aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…