相关论文: Understanding Representations Pretrained with Auxi…

A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in developing the neural flexibility for creative problem…

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin…

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

Embodied AI agents require a fine-grained understanding of the physical world mediated through visual and language inputs. Such capabilities are difficult to learn solely from task-specific data. This has led to the emergence of pre-trained…

Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited.…

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems…

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular…

One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of…

Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on…

Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting expert demonstrations can be expensive. Recent work in…

Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent perceives and represents the world. To learn powerful representations, an agent should actively explore…

Latent representations are used extensively for downstream tasks, such as visualization, interpolation or feature extraction of deep learning models. Invariant and equivariant neural networks are powerful and well-established models for…

A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted…

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations,…

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…

We are witnessing significant progress on perception models, specifically those trained on large-scale internet images. However, efficiently generalizing these perception models to unseen embodied tasks is insufficiently studied, which will…

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

The benefit of pretrained autoencoders for reinforcement learning in comparison to training on raw observations is already known [1]. In this paper, we address the generation of a compact and information-rich state representation. In…