相关论文: Revisiting DAgger in the Era of LLM-Agents

A popular paradigm for training LM agents relies on imitation learning, fine-tuning on expert trajectories. However, we show that the off-policy nature of imitation learning for multi-turn LM agents suffers from the fundamental limitation…

Imitation learning has proven to be useful for many real-world problems, but approaches such as behavioral cloning suffer from data mismatch and compounding error issues. One attempt to address these limitations is the DAgger algorithm,…

Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during policy learning, such as a human performing a novel task or an…

Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning.…

Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered by covariate shift and the need for continuous expert monitoring to recover from failures…

Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the…

In this paper, We Apply Reinforcement learning (RL) techniques to train a realistic biomechanical model to work with different people and on different walking environments. We benchmarking 3 RL algorithms: Deep Deterministic Policy Gradient…

Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying…

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

In this work, we propose a novel memory-based multi-agent meta-learning architecture and learning procedure that allows for learning of a shared communication policy that enables the emergence of rapid adaptation to new and unseen…

Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more convenient and…

Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer…

Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies could drive robots into unseen out-of-distribution (OOD) states in the training set,…

On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between…

A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that are not present in the expert demonstrations, the policy fails, leading to degenerate…

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for…

Many tasks within NLP can be framed as sequential decision problems, ranging from sequence tagging to text generation. However, for many tasks, the standard training methods, including maximum likelihood (teacher forcing) and scheduled…

Most multi-agent reinforcement learning (MARL) methods are limited in the scale of problems they can handle. With increasing numbers of agents, the number of training iterations required to find the optimal behaviors increases exponentially…

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view…

One way to approach end-to-end autonomous driving is to learn a policy function that maps from a sensory input, such as an image frame from a front-facing camera, to a driving action, by imitating an expert driver, or a reference policy.…