相关论文: Generalizing to New Tasks via One-Shot Composition…

The development of a generalist agent capable of solving a wide range of sequential decision-making tasks remains a significant challenge. We address this problem in a cross-agent setup where agents share the same observation space but…

A key requirement for generalist robots is compositional generalization - the ability to combine atomic skills to solve complex, long-horizon tasks. While prior work has primarily focused on synthesizing a planner that sequences pre-learned…

We study zero-shot generalization in reinforcement learning-optimizing a policy on a set of training tasks to perform well on a similar but unseen test task. To mitigate overfitting, previous work explored different notions of invariance to…

Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning…

Agents of general intelligence deployed in real-world scenarios must adapt to ever-changing environmental conditions. While such adaptive agents may leverage engineered knowledge, they will require the capacity to construct and evaluate…

Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few…

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling…

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle…

Imitation learning is a widely used policy learning method that enables intelligent agents to acquire complex skills from expert demonstrations. The input to the imitation learning algorithm is usually composed of both the current…

Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts.…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation…

Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to…

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.…

While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralization, where the agent…

Goal instructions for autonomous AI agents cannot assume that objects have unique names. Instead, objects in goals must be referred to by providing suitable descriptions. However, this raises problems in both classical planning and…

Continual learning aims to sequentially learn new tasks without forgetting previous tasks' knowledge (catastrophic forgetting). One factor that can cause forgetting is the interference between the gradients on losses from different tasks.…

This work presents an incremental learning approach for autonomous agents to learn new tasks in a non-stationary environment. Updating a DNN model-based agent to learn new target tasks requires us to store past training data and needs a…

The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess the models' input-output behavior. However, that does not…