Related papers: SEIHAI: A Sample-efficient Hierarchical AI for the…
In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. An aspirational goal is to construct self-improving robots: robots that can learn and improve on their own, from…
Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance. To address this, we introduce a practical algorithm for incorporating…
Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced…
Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…
Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? These scenarios force us to evaluate the trade-off between collective rules…
Semi-supervised learning approaches have emerged as an active area of research to combat the challenge of obtaining large amounts of annotated data. Towards the goal of improving the performance of semi-supervised learning methods, we…
Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and…
Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…
Efficient learning in the environment with sparse rewards is one of the most important challenges in Deep Reinforcement Learning (DRL). In continuous DRL environments such as robotic arms control, Hindsight Experience Replay (HER) has been…
One of the fundamental quests of AI is to produce agents that coordinate well with humans. This problem is challenging, especially in domains that lack high quality human behavioral data, because multi-agent reinforcement learning (RL)…
Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy…
Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to…
The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…
Deep Reinforcement Learning has been successfully applied to learn robotic control. However, the corresponding algorithms struggle when applied to problems where the agent is only rewarded after achieving a complex task. In this context,…
The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…
In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby…
Meta-Reinforcement Learning (MRL) is a promising framework for training agents that can quickly adapt to new environments and tasks. In this work, we study the MRL problem under the policy gradient formulation, where we propose a novel…
Many real-world applications can be formulated as multi-agent cooperation problems, such as network packet routing and coordination of autonomous vehicles. The emergence of deep reinforcement learning (DRL) provides a promising approach for…
Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time. Hierarchical reinforcement learning can facilitate exploration by reducing…