Related papers: Training Language Agents to Learn from Experience
Large Language Models (LLMs) serve not only as chatbots but as key components in agent systems, where their common-sense knowledge significantly impacts performance as language-based planners for situated or embodied action. We assess LLMs'…
Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…
We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as "elf-bench"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions. Learning from…
We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…
The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abilities are…
Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…
Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive…
In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance. While ICL has been highly successful…
Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…
Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…
Social learning is a key component of human and animal intelligence. By taking cues from the behavior of experts in their environment, social learners can acquire sophisticated behavior and rapidly adapt to new circumstances. This paper…
Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in these complex tasks. Moreover, current LLM agents are not…
Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…
We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things…
Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies,…
A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward model to emulate human feedback, distinct from the language…
Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…
Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast,…
Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated…