Related papers: Latent Skill Planning for Exploration and Transfer

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

The sustainable foraging problem is a dynamic environment testbed for exploring the forms of agent cognition in dealing with social dilemmas in a multi-agent setting. The agents need to resist the temptation of individual rewards through…

Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most…

We study online learning for optimal allocation when the resource to be allocated is time. %Examples of possible applications include job scheduling for a computing server, a driver filling a day with rides, a landlord renting an estate,…

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to…

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great…

Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for…

One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration mechanism that…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely. We accomplish this by using a learned world model of the agent system to forecast…

In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning…

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

We treat the problem of autonomous acquisition of manipulation skills where problem-solving strategies are initially available only for a narrow range of situations. We propose to extend the range of solvable situations by autonomous…

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries…

Despite the recent progress in deep learning and reinforcement learning, transfer and generalization of skills learned on specific tasks is very limited compared to human (or animal) intelligence. The lifelong, incremental building of…

Designing robotic agents to perform open vocabulary tasks has been the long-standing goal in robotics and AI. Recently, Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary…