相关论文: Quantile QT-Opt for Risk-Aware Vision-Based Roboti…

To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of…

A robot operating in unstructured environments must be able to discriminate between different grasping styles depending on the prospective manipulation task. Having a system that allows learning from remote non-expert demonstrations can…

In this work, we propose a hybrid hierarchical control framework for reactive dexterous grasping that explicitly decouples high-level spatial intent from low-level joint execution. We introduce a multi-agent reinforcement learning…

Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progress may be easily reversed. We develop the SPOT framework, which explores within action safety zones,…

Development of navigation algorithms is essential for the successful deployment of robots in rapidly changing hazardous environments for which prior knowledge of configuration is often limited or unavailable. Use of traditional…

Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading…

General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to…

This study evaluates the application of a discrete action space reinforcement learning method (Q-learning) to the continuous control problem of robot inverted pendulum balancing. To speed up the learning process and to overcome technical…

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs…

Optimized control of quantum networks is essential for enabling distributed quantum applications with strict performance requirements. In near-term architectures with constrained hardware, effective control may determine the feasibility of…

We address the problem of directional semantic grasping, that is, grasping a specific object from a specific direction. We approach the problem using deep reinforcement learning via a double deep Q-network (DDQN) that learns to map…

Deep reinforcement learning continues to show tremendous potential in achieving task-level autonomy, however, its computational and energy demands remain prohibitively high. In this paper, we tackle this problem by applying quantization to…

Robotic manipulation in industrial scenarios such as construction commonly faces uncertain observations in which the state of the manipulating object may not be accurately captured due to occlusions and partial observables. For example,…

Deploying learned control policies on humanoid robots is challenging: policies that appear robust in simulation can execute confidently in out-of-distribution (OOD) states after Sim-to-Real transfer, leading to silent failures that risk…

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample…

Meta-reinforcement learning algorithms provide a data-driven way to acquire policies that quickly adapt to many tasks with varying rewards or dynamics functions. However, learned meta-policies are often effective only on the exact task…

Due to its property of not requiring prior knowledge of the environment, reinforcement learning has significant potential for quantum control problems. In this work, we investigate the effectiveness of continuous control policies based on…

Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under…

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…

Distributional reinforcement learning (DRL) extends the value-based approach by approximating the full distribution over future returns instead of the mean only, providing a richer signal that leads to improved performances. Quantile…