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

A large body of work in behavioral fields attempts to develop models that describe the way people, as opposed to rational agents, make decisions. A recent Choice Prediction Competition (2015) challenged researchers to suggest a model that…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a reward function takes considerable hand…

We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and…

Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in…

LLM-based agents have shown promise in various cooperative and strategic reasoning tasks, but their effectiveness in competitive multi-agent environments remains underexplored. To address this gap, we introduce PillagerBench, a novel…

While Vision-Language Models (VLMs) hold promise for tasks requiring extensive collaboration, traditional multi-agent simulators have facilitated rich explorations of an interactive artificial society that reflects collective behavior.…

Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies.…

We consider the problem of making AI agents that collaborate well with humans in partially observable fully cooperative environments given datasets of human behavior. Inspired by piKL, a human-data-regularized search method that improves…

Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems. However, injecting human knowledge into an RL agent may require extensive effort and expertise on the human designer's part. To date, human…

We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and…

Learning from demonstration (LfD) techniques seek to enable novice users to teach robots novel tasks in the real world. However, prior work has shown that robot-centric LfD approaches, such as Dataset Aggregation (DAgger), do not perform…

A robot as a coworker or a cohabitant is becoming mainstream day-by-day with the development of low-cost sophisticated hardware. However, an accompanying software stack that can aid the usability of the robotic hardware remains the…

Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated using imitation learning, where the agent learns to imitate…

Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences. We hypothesize that state-of-the-art instructional image editing models, where outputs are generated based on…

Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various…

Learning motor skills for sports or performance driving is often done with professional instruction from expert human teachers, whose availability is limited. Our goal is to enable automated teaching via a learned model that interacts with…

We propose a lifelong learning system that has the ability to reuse and transfer knowledge from one task to another while efficiently retaining the previously learned knowledge-base. Knowledge is transferred by learning reusable skills to…

Developing effective Multi-Agent Systems (MAS) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of Multi-Agent Deep Reinforcement Learning (MADRL) in cooperative MAS, one…

We study an online decision making problem where on each round a learner chooses a list of items based on some side information, receives a scalar feedback value for each individual item, and a reward that is linearly related to this…