Hiql: Offline goal-conditioned rl with latent states as actions
Unsupervised pre-training has recently become the bedrock for computer vision and natural
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …
Curriculum-guided hindsight experience replay
In off-policy deep reinforcement learning, it is usually hard to collect sufficient successful
experiences with sparse rewards to learn from. Hindsight experience replay (HER) enables …
experiences with sparse rewards to learn from. Hindsight experience replay (HER) enables …
Reinforcement learning with multiple relational attention for solving vehicle routing problems
In this article, we study the reinforcement learning (RL) for vehicle routing problems (VRPs).
Recent works have shown that attention-based RL models outperform recurrent neural …
Recent works have shown that attention-based RL models outperform recurrent neural …
Exploration in deep reinforcement learning: From single-agent to multiagent domain
Deep reinforcement learning (DRL) and deep multiagent reinforcement learning (MARL)
have achieved significant success across a wide range of domains, including game artificial …
have achieved significant success across a wide range of domains, including game artificial …
Improving unsupervised visual program inference with code rewriting families
A Ganeshan, RK Jones… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Programs offer compactness and structure that makes them an attractive representation for
visual data. We explore how code rewriting can be used to improve systems for inferring …
visual data. We explore how code rewriting can be used to improve systems for inferring …
Exploration via hindsight goal generation
Goal-oriented reinforcement learning has recently been a practical framework for robotic
manipulation tasks, in which an agent is required to reach a certain goal defined by a …
manipulation tasks, in which an agent is required to reach a certain goal defined by a …
A case study of deep reinforcement learning for engineering design: Application to microfluidic devices for flow sculpting
Efficient exploration of design spaces is highly sought after in engineering applications. A
spectrum of tools has been proposed to deal with the computational difficulties associated …
spectrum of tools has been proposed to deal with the computational difficulties associated …
Deep reinforcement learning for real-time assembly planning in robot-based prefabricated construction
The adoption of robotics is promising to improve the efficiency, quality, and safety of
prefabricated construction. Besides technologies that improve the capability of a single …
prefabricated construction. Besides technologies that improve the capability of a single …
Towards distraction-robust active visual tracking
In active visual tracking, it is notoriously difficult when distracting objects appear, as
distractors often mislead the tracker by occluding the target or bringing a confusing …
distractors often mislead the tracker by occluding the target or bringing a confusing …
Robot skill learning and the data dilemma it faces: a systematic review
Purpose Compared with traditional methods relying on manual teaching or system
modeling, data-driven learning methods, such as deep reinforcement learning and imitation …
modeling, data-driven learning methods, such as deep reinforcement learning and imitation …