Apr 20[ACM TELO 2021 / NeurIPS 2020 Workshop] Reusability and Transferability of Macro Actions for Reinforcement LearningACM TELO 2021 Full Paper Introduction In conventional Reinforcement Learning (RL) methods, agents are restricted to make decisions at each timestep. However, the rewards in RL training are intrinsically biased toward short-term goals due to discounting. Such situations are further exacerbated by the greedy nature of the agents which simply follow…Reinforcement Learning7 min readReinforcement Learning7 min read

Mar 17[ICLR 2022] Denoising Likelihood Score Matching for Condition Score-Based Data GenerationICLR 2022 Full Paper Keywords Score-based generative model, conditional sampling, DLSM Introduction Score-based generative models are probabilistic generative models that estimate score functions, i.e., the gradients of the log density for some given data distribution. According to the definition of the pioneering work, the process of training score-based generative models is called…Machine Learning8 min readMachine Learning8 min read

Jan 31[AAMAS 2018] A Deep Policy Inference Q-Network for Multi-Agent SystemsAAMAS 2018 Full Paper Keywords Deep reinforcement learning, multi-agent system (MAS), deep policy inference Q-network (DPIQN) Introduction Modeling and exploiting other agents’ behaviors in a multi-agent system (MAS) have received much attention in the past decade. In such a system, the environment perceived by each agent, however, changes over time due to…Deep Reinforcement8 min readDeep Reinforcement8 min read

Dec 24, 2021[CoRL 2019] Adversarial Active Exploration for Inverse Dynamics Model LearningCoRL 2019 Full Paper Keywords deep reinforcement learning, inverse dynamic model, intrinsic reward, adversarial learning, exploration Introduction Over the past decade, inverse dynamics models have shown considerable successes in robotic control and even in humanoid robots. The main objective of an inverse dynamics model is to predict the control action between two…Reinforcement Learning6 min readReinforcement Learning6 min read

Nov 25, 2021[NeurIPS 2018] Diversity-Driven Exploration Strategy for Deep Reinforcement LearningNeurIPS 2018 Full Paper Demonstration Video Keywords Deep reinforcement learning, Exploration Introduction Efficient exploration remains a challenging research problem in reinforcement learning (RL), especially when an environment contains large state spaces, deceptive or sparse rewards. In an environment with deceptive rewards, an agent can be trapped in local optima, and never discover alternate…Deep Learning7 min readDeep Learning7 min read

Sep 26, 2021[ICML 2021 Spotlight] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-LearningICML 2021 Full Paper ICML Presentation Video Demonstration Video Keywords DFAC, Multi-agent reinforcement learning, SMAC, distributional Q-learning, value function factorization, quantile mixture Introduction In multi-agent reinforcement learning (MARL), the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents. One of popular research directions…Reinforcement Learning7 min readReinforcement Learning7 min read

Aug 26, 2021[CVPR 2018] Dynamic Video Segmentation Network2018 CVPR Full Paper Demonstration Keywords Semantic segmentation, optical flow, decision network, DVSNet, confidence score, adaptive key frame scheduling policy, real-time inference. Introduction In recent years, semantic image segmentation has achieved an unprecedented performance via using deep convolutional neural networks (DCNNs). Accurate semantic segmentation enables a number of applications which demand pixel-level…Machine Learning11 min readMachine Learning11 min read

Aug 3, 2021[IJCAI 2018] Virtual-to-Real: Learning to Control in Visual Semantic Segmentation2018 IJCAI Full Paper Demonstration Keywords Sim-to-real transfer, virtual-to-real transfer, mid-level representation, meta representation, semantic segmentation, deep reinforcement learning, A3C. NVIDIA Jetson Developer Challenge The technique proposed in this paper has also won the grand prize (1st place) at NVIDIA Jetson Developer Challenger in 2018. …Reinforcement Learning11 min readReinforcement Learning11 min read

Jul 12, 2021[ICCD 2019] A Distributed Scheme for Accelerating Semantic Video Segmentation on An Embedded Cluster2019 ICCD Full Paper Demonstration Video Keywords: DVSNet, edge computing, semantic segmentation, distributed computing, embedded system, embedded cluster, optical flow, hierarchical architecture, decision…Machine Learning10 min readMachine Learning10 min read

Jun 21, 2021[ICRA 2021] Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture2021 ICRA Full Paper Demonstration Video Introduction Reinforcement learning (RL) is a training process to make a sequence of decisions and try to take actions in an environment to maximize the cumulative reward. …Machine Learning8 min readMachine Learning8 min read