相关论文: Generalization to New Actions in Reinforcement Lea…

An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that…

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train…

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset…

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…

A hallmark of intelligence is the ability to deduce general principles from examples, which are correct beyond the range of those observed. Generalized Planning deals with finding such principles for a class of planning problems, so that…

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes), by sharing information of attributes between different objects. Attributes are artificially annotated for objects and…

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are…

The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack…

We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions. The input LTL formulas have never been seen before, yet the network…

Learning to use tools to solve a variety of tasks is an innate ability of humans and has been observed of animals in the wild. However, the underlying mechanisms that are required to learn to use tools are abstract and widely contested in…

Humans have an impressive ability to reason about new concepts and experiences from just a single example. In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure,…

Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically observe that an agent trained on many variations (a…

The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a…

Reinforcement learning (RL) agents are widely used for solving complex sequential decision making tasks, but still exhibit difficulty in generalizing to scenarios not seen during training. While prior online approaches demonstrated that…

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around:…

Learning a control policy capable of adapting to time-varying and potentially evolving system dynamics has been a great challenge to the mainstream reinforcement learning (RL). Mainly, the ever-changing system properties would continuously…

Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generative models to combat…