相关论文: Excavation Reinforcement Learning Using Geometric …

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally extended tasks…

Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy of 3D representations with 2D representations across…

Standard model-free deep reinforcement learning (RL) algorithms sample a new initial state for each trial, allowing them to optimize policies that can perform well even in highly stochastic environments. However, problems that exhibit…

Geometric properties can be leveraged to stabilize and speed reinforcement learning. Existing examples include encoding symmetry structure, geometry-aware data augmentation, and enforcing structural restrictions. In this paper, we take a…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Manipulating objects is a hallmark of human intelligence, and an important task in domains such as robotics. In principle, Reinforcement Learning (RL) offers a general approach to learn object manipulation. In practice, however, domains…

Picking cluttered general objects is a challenging task due to the complex geometries and various stacking configurations. Many prior works utilize pose estimation for picking, but pose estimation is difficult on cluttered objects. In this…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Active matter refers to systems composed of self-propelled entities that consume energy to produce motion, exhibiting complex non-equilibrium dynamics that challenge traditional models. With the rapid advancements in machine learning,…

Physics-based manipulation in clutter involves complex interaction between multiple objects. In this paper, we consider the problem of learning, from interaction in a physics simulator, manipulation skills to solve this multi-step…

Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is how to make RL cope with partial observability which is…

The design of materials structure for optimizing functional properties and potentially, the discovery of novel behaviors is a keystone problem in materials science. In many cases microstructural models underpinning materials functionality…

Interest in reinforcement learning (RL) for large-scale systems, comprising extensive populations of intelligent agents interacting with heterogeneous environments, has surged significantly across diverse scientific domains in recent years.…

We consider a problem in which the trajectory of a mobile 3D sensor must be optimized so that certain objects are both found in the overall scene and covered by the point cloud, as fast as possible. This problem is called target search and…

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Recently, deep reinforcement learning (RL) has been proposed to learn the tractography procedure and train agents to reconstruct the structure of the white matter without manually curated reference streamlines. While the performances…

Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable,…

Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…