Search Results for author:
Found 40 papers, 16 papers with code
On the Impact of Data Quality on Image Classification Fairness
By adding noise to the original datasets, we can explore the relationship between the quality of the training data and the fairness of the output of the models trained on that data.
Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping
We validate our insight on a range of RL tasks and show its improvement over baselines: (1) In offline RL, the conservative exploitation leads to improved performance based on off-the-shelf algorithms; (2) In online continuous control, multiple value functions with different shifting constants can be used to tackle the exploration-exploitation dilemma for better sample efficiency; (3) In discrete control tasks, a negative reward shifting yields an improvement over the curiosity-based exploration method.
Relative Policy-Transition Optimization for Fast Policy Transfer
Then, integrating the two algorithms offers the complete algorithm Relative Policy-Transition Optimization (RPTO), in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer.
RORL: Robust Offline Reinforcement Learning via Conservative Smoothing
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks.
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm.
Dynamic Bottleneck for Robust Self-Supervised Exploration
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards.
Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning
We provide comprehensive analysis and experiments to elaborate the effect of each component in affecting the agent performance, and demonstrate that the proposed and adopted techniques are important to achieve superior performance in general end-to-end FPS games.
Reward Shifting for Optimistic Exploration and Conservative Exploitation
We verify our insight on a range of tasks: (1) In offline RL, the conservative exploitation leads to improved learning performance based on off-the-shelf algorithms; (2) In online continuous control, multiple value functions with different shifting constants can be used to trade-off between exploration and exploitation thus improving learning efficiency; (3) In online RL with discrete action space, a negative reward shifting brings an improvement over the previous curiosity-based exploration method.
Bootstrapped Hindsight Experience replay with Counterintuitive Prioritization
In this paper, inspired by Bootstrapped DQN, we use multiple heads in DDPG and take advantage of the diversity and uncertainty among multiple heads to improve the data efficiency with relabeled goals.
A General Theory of Relativity in Reinforcement Learning
We propose a new general theory measuring the relativity between two arbitrary Markov Decision Processes (MDPs) from the perspective of reinforcement learning (RL).
Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning
In multi-agent reinforcement learning, the behaviors that agents learn in a single Markov Game (MG) are typically confined to the given agent number (i. e., population size).
Multi-agent Reinforcement Learning
reinforcement-learning
+1
MHER: Model-based Hindsight Experience Replay
Replacing original goals with virtual goals generated from interaction with a trained dynamics model leads to a novel relabeling method, model-based relabeling (MBR).
Principled Exploration via Optimistic Bootstrapping and Backward Induction
In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I).
Magnon-mediated interlayer coupling in an all-antiferromagnetic junction
The interlayer coupling mediated by fermions in ferromagnets brings about parallel and anti-parallel magnetization orientations of two magnetic layers, resulting in the giant magnetoresistance, which forms the foundation in spintronics and accelerates the development of information technology.
Materials Science
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
We show that with orders of less computation scale, a faithful reimplementation of AlphaStar's methods can not succeed and the proposed techniques are necessary to ensure TStarBot-X's competitive performance.
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems.
Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded.
Object Tracking by Least Spatiotemporal Searches
This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location.
Triaging moderate COVID-19 and other viral pneumonias from routine blood tests
The COVID-19 is sweeping the world with deadly consequences.
OccuSeg: Occupancy-aware 3D Instance Segmentation
3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days.
Ranked #1 on
3D Instance Segmentation
on SceneNN
Curriculum-guided Hindsight Experience Replay
This ``Goal-and-Curiosity-driven Curriculum Learning'' leads to ``Curriculum-guided HER (CHER)'', which adaptively and dynamically controls the exploration-exploitation trade-off during the learning process via hindsight experience selection.
LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
A great challenge in cooperative decentralized multi-agent reinforcement learning (MARL) is generating diversified behaviors for each individual agent when receiving only a team reward.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Convolutional Neural Network for Convective Storm Nowcasting Using 3D Doppler Weather Radar Data
On the first layer of CNN, a cross-channel 3D convolution was proposed to fuse 3D raw data.
A Three-dimensional Convolutional-Recurrent Network for Convective Storm Nowcasting
Very short-term convective storm forecasting, termed nowcasting, has long been an important issue and has attracted substantial interest.
A Random Gossip BMUF Process for Neural Language Modeling
One important challenge of training an NNLM is to leverage between scaling the learning process and handling big data.
Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition
In this work, we propose to train pruned language models for the word classes to replace the slots in the root n-gram.
Arena: a toolkit for Multi-Agent Reinforcement Learning
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research.
GFF: Gated Fully Fusion for Semantic Segmentation
Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel.
Ranked #25 on
Semantic Segmentation
on Cityscapes test
RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
Direct image-to-image alignment that relies on the optimization of photometric error metrics suffers from limited convergence range and sensitivity to lighting conditions.
Exponentially Weighted Imitation Learning for Batched Historical Data
We consider deep policy learning with only batched historical trajectories.
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE
Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space.
Candidates vs. Noises Estimation for Large Multi-Class Classification Problem
This paper proposes a method for multi-class classification problems, where the number of classes K is large.
Beyond SIFT using Binary features for Loop Closure Detection
The proposed system originates from our previous work Multi-Index hashing for Loop closure Detection (MILD), which employs Multi-Index Hashing (MIH)~\cite{greene1994multi} for Approximate Nearest Neighbor (ANN) search of binary features.
MILD: Multi-Index hashing for Loop closure Detection
Loop Closure Detection (LCD) has been proved to be extremely useful in global consistent visual Simultaneously Localization and Mapping (SLAM) and appearance-based robot relocalization.
Application of Multi-channel 3D-cube Successive Convolution Network for Convective Storm Nowcasting
This paper describes the first attempt to nowcast storm initiation, growth, and advection simultaneously under a deep learning framework using multi-source meteorological data.
Action2Activity: Recognizing Complex Activities from Sensor Data
As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life.
A Machine Learning Nowcasting Method based on Real-time Reanalysis Data
Despite marked progress over the past several decades, convective storm nowcasting remains a challenge because most nowcasting systems are based on linear extrapolation of radar reflectivity without much consideration for other meteorological fields.
Local Uncertainty Sampling for Large-Scale Multi-Class Logistic Regression
A major challenge for building statistical models in the big data era is that the available data volume far exceeds the computational capability.
