Search Results for author:
Found 11 papers, 3 papers with code
Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning
To address this challenge, previous imitation learning methods exploit task-specific knowledge, e. g., labeling demonstrations manually or specifying termination conditions for each sub-task.
Interpreting Adaptive Gradient Methods by Parameter Scaling for Learning-Rate-Free Optimization
We address the challenge of estimating the learning rate for adaptive gradient methods used in training deep neural networks.
Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments
Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies.
Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge
In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge.
SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations
Moreover, we show that our method can retrain the agent to recover from OOD situations even when in-distribution states are difficult to visit through exploration.
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed.
Ranked #1 on
Long-tail Learning
on iNaturalist 2018
(using extra training data)
Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning
Our proposed method derives the variational lower bound of the situational mutual information to optimize it.
GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving
Applying reinforcement learning to autonomous driving entails particular challenges, primarily due to dynamically changing traffic flows.
Learning Neural Processes on the Fly
In this paper, we propose a new algorithm called anytime neural processes that combines DNNs and SNNs and can work in both low-data and high-data regimes.
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning.
A Robotic Dating Coaching System Leveraging Online Communities Posts
Can a robot be a personal dating coach?
