Search Results for author:
Found 15 papers, 4 papers with code
Pushing the Limits of Machine Design: Automated CPU Design with AI
By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours.
Online Prototype Alignment for Few-shot Policy Transfer
Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment.
Ultra-low Precision Multiplication-free Training for Deep Neural Networks
The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications.
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Object-Category Aware Reinforcement Learning
Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL.
Neural Program Synthesis with Query
In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.
Distilling Object Detectors with Feature Richness
Second, these methods imitate some features which are mistakenly regarded as the background by the teacher detector.
Learning Controllable Elements Oriented Representations for Reinforcement Learning
Deep Reinforcement Learning (deep RL) has been successfully applied to solve various decision-making problems in recent years.
Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment
In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.
Domain-Specific Suppression for Adaptive Object Detection
The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one.
Fixed-Point Back-Propagation Training
Recent emerged quantization technique (i. e., using low bit-width fixed-point data instead of high bit-width floating-point data) has been applied to inference of deep neural networks for fast and efficient execution.
DWM: A Decomposable Winograd Method for Convolution Acceleration
In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers.
Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description
This paper contributes to: 1)The first in-depth study of the weakness inherent in data-driven static fusion methods for video captioning.
