Related papers: Invariant Causal Imitation Learning for Generaliza…
In this paper, we propose a robust imitation learning (IL) framework that improves the robustness of IL when environment dynamics are perturbed. The existing IL framework trained in a single environment can catastrophically fail with…
Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly interact with the environment and may implicitly perturb the…
We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…
Policy learning under action constraints plays a central role in ensuring safe behaviors in various robot control and resource allocation applications. In this paper, we study a new problem setting termed Action-Constrained Imitation…
In-context imitation learning (ICIL) is a new paradigm that enables robots to generalize from demonstrations to unseen tasks without retraining. A well-structured action representation is the key to capturing demonstration information…
Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments.…
We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrinsics significantly improves generalization across viewpoints…
Deep imitation learning enables robots to learn from expert demonstrations to perform tasks such as lane following or obstacle avoidance. However, in the traditional imitation learning framework, one model only learns one task, and thus it…
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…
Learning representations purely from observations concerns the problem of learning a low-dimensional, compact representation which is beneficial to prediction models. Under the hypothesis that the intrinsic latent factors follow some casual…
Imitation learning attracts much attention for its ability to allow robots to quickly learn human manipulation skills through demonstrations. However, in the real world, human demonstrations often exhibit random behavior that is not…
We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on…
When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of…
Imitation Learning from observation describes policy learning in a similar way to human learning. An agent's policy is trained by observing an expert performing a task. While many state-only imitation learning approaches are based on…
In this paper, we discuss structure learning of causal networks from multiple data sets obtained by external intervention experiments where we do not know what variables are manipulated. For example, the conditions in these experiments are…
Many tasks in practice require the collaboration of multiple agents through reinforcement learning. In general, cooperative multiagent reinforcement learning algorithms can be classified into two paradigms: Joint Action Learners (JALs) and…
In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange…
Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or they at least require…
Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in…