Related papers: Accelerating Robotic Reinforcement Learning via Pa…
Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents…
We introduce Large Language Model-Assisted Preference Prediction (LAPP), a novel framework for robot learning that enables efficient, customizable, and expressive behavior acquisition with minimum human effort. Unlike prior approaches that…
Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information…
In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode. Typical applications include robotic control with limited energy…
Autonomous vehicles inevitably encounter a vast array of scenarios in real-world environments. Addressing long-tail scenarios, particularly those involving intensive interactions with numerous traffic participants, remains one of the most…
In reinforcement learning (RL) research, simulations enable benchmarks between algorithms, as well as prototyping and hyper-parameter tuning of agents. In order to promote RL both in research and real-world applications, frameworks are…
Humans can abstract prior knowledge from very little data and use it to boost skill learning. In this paper, we propose routine-augmented policy learning (RAPL), which discovers routines composed of primitive actions from a single…
Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…
Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…
Grasping by a robot in unstructured environments is deemed a critical challenge because of the requirement for effective adaptation to a wide variation in object geometries, material properties, and other environmental factors. In this…
Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…
Robotic manipulation holds the potential to replace humans in the execution of tedious or dangerous tasks. However, control-based approaches are not suitable due to the difficulty of formally describing open-world manipulation in reality,…
Reinforcement learning in large-scale environments is challenging due to the many possible actions that can be taken in specific situations. We have previously developed a means of constraining, and hence speeding up, the search process…
Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization…
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…
There is an increased demand for task automation in robots. Contact-rich tasks, wherein multiple contact transitions occur in a series of operations, are extensively being studied to realize high accuracy. In this study, we propose a…
Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing. However, this shaped reward introduces learning biases, which reduces the…
Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…
While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…
Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomously learns actions to maximize its reward. Existing…