相关论文: Training Language Agents to Learn from Experience

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned…

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations…

This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize that two key…

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…

Artificial intelligence systems increasingly involve continual learning to enable flexibility in general situations that are not encountered during system training. Human interaction with autonomous systems is broadly studied, but research…

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often…

Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently…

Consider the problem setting of Interaction-Grounded Learning (IGL), in which a learner's goal is to optimally interact with the environment with no explicit reward to ground its policies. The agent observes a context vector, takes an…

With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to…

In this study, we address the issue of enabling an artificial intelligence agent to execute complex language instructions within virtual environments. In our framework, we assume that these instructions involve intricate linguistic…

Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or…

In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…

Digital tool-based agents, powered by Large Language Models (LLMs), that invoke external Application Programming Interfaces (APIs) often rely on documentation to understand API functionality. However, such documentation is frequently…

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL…