相关论文: Combining Learning from Human Feedback and Knowled…

An appropriate reward function is of paramount importance in specifying a task in reinforcement learning (RL). Yet, it is known to be extremely challenging in practice to design a correct reward function for even simple tasks.…

Behavioral cloning uses a dataset of demonstrations to learn a policy. To overcome computationally expensive training procedures and address the policy adaptation problem, we propose to use latent spaces of pre-trained foundation models to…

Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by…

To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation protocols often emphasize benchmark performance with…

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

Human-Computer Interaction has been shown to lead to improvements in machine learning systems by boosting model performance, accelerating learning and building user confidence. In this work, we aim to alleviate the expectation that human…

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by…

In open-world environments like Minecraft, existing agents face challenges in continuously learning structured knowledge, particularly causality. These challenges stem from the opacity inherent in black-box models and an excessive reliance…

Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs),…

The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy. However, execution of instructions in real or simulated environments requires verification of the feasibility of…

How can we design Natural Language Processing (NLP) systems that learn from human feedback? There is a growing research body of Human-in-the-loop (HITL) NLP frameworks that continuously integrate human feedback to improve the model itself.…

Although virtual agents are increasingly situated in environments where natural language is the most effective mode of interaction with humans, these exchanges are rarely used as an opportunity for learning. Leveraging language interactions…

Procedural content generation for games is a growing trend in both research and industry, even though there is no consensus of how good content looks, nor how to automatically evaluate it. A number of metrics have been developed in the…

Imitation learning from human demonstrations is a promising paradigm for teaching robots manipulation skills in the real world. However, learning complex long-horizon tasks often requires an unattainable amount of demonstrations. To reduce…

Inferential decision-making algorithms typically assume that an underlying probabilistic model of decision alternatives and outcomes may be learned a priori or online. Furthermore, when applied to robots in real-world settings they often…

While large language models (LLMs) have shown promising capabilities as zero-shot planners for embodied agents, their inability to learn from experience and build persistent mental models limits their robustness in complex open-world…

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…

Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for…

It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract…

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by…