Minne Li
YOU?
Author Swipe
View article: Impact of Short-Term Total Dissolved Gas Supersaturation on Cognitive Functions and Swimming Performance in Medaka (Oryzias latipes)
Impact of Short-Term Total Dissolved Gas Supersaturation on Cognitive Functions and Swimming Performance in Medaka (Oryzias latipes) Open
During the flood season, high dam operations for flood discharge result in total dissolved gas (TDG) supersaturation. This condition causes gas bubble trauma (GBT) and can even lead to fish mortality, posing a significant threat to downstr…
View article: Swimming ability of cyprinid species (subfamily schizothoracinae) at high altitude
Swimming ability of cyprinid species (subfamily schizothoracinae) at high altitude Open
The primary objective of this investigation was to study the effect of altitude on fish swimming ability. Different species were tested to ensure that the differences observed are not associated with a single species. Fish critical swimmin…
View article: Evaluation of Volitional Swimming Behavior of Schizothorax prenanti Using an Open-Channel Flume with Spatially Heterogeneous Turbulent Flow
Evaluation of Volitional Swimming Behavior of Schizothorax prenanti Using an Open-Channel Flume with Spatially Heterogeneous Turbulent Flow Open
Effective fishway design requires knowledge of fish swimming behavior in streams and channels. Appropriate tests with near-natural flow conditions are required to assess the interaction between fish behavior and turbulent flows. In this st…
View article: A Game-Theoretic Approach to Multi-Agent Trust Region Optimization
A Game-Theoretic Approach to Multi-Agent Trust Region Optimization Open
Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement guarantee at every iteration. Nonetheless, when applied in multi-agent settings, the guarantee of trust …
View article: Learning in Nonzero-Sum Stochastic Games with Potentials
Learning in Nonzero-Sum Stochastic Games with Potentials Open
Multi-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of…
View article: Bi-Level Actor-Critic for Multi-Agent Coordination
Bi-Level Actor-Critic for Multi-Agent Coordination Open
Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when mult…
View article: Compositional ADAM: An Adaptive Compositional Solver
Compositional ADAM: An Adaptive Compositional Solver Open
In this paper, we present C-ADAM, the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values. We proof that C-ADAM converges to a stationary point in $\mathcal{O}(δ^{-2.25})$ with $δ$ …
View article: Multi-View Reinforcement Learning
Multi-View Reinforcement Learning Open
This paper is concerned with multi-view reinforcement learning (MVRL), which allows for decision making when agents share common dynamics but adhere to different observation models. We define the MVRL framework by extending partially obser…
View article: Bi-level Actor-Critic for Multi-agent Coordination
Bi-level Actor-Critic for Multi-agent Coordination Open
Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when mult…
View article: Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning Open
A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified proble…
View article: Joint Perception and Control as Inference with an Object-based Implementation
Joint Perception and Control as Inference with an Object-based Implementation Open
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for par…
View article: Joint Learning of Unsupervised Object-Based Perception and Control
Joint Learning of Unsupervised Object-Based Perception and Control Open
This paper is concerned with object-based perception control (OPC), which allows for joint optimization of hierarchical object-based perception and decision making. We define the OPC framework by extending the Bayesian brain hypothesis to …
View article: Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning Open
A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified proble…
View article: Mean Field Multi-Agent Reinforcement Learning
Mean Field Multi-Agent Reinforcement Learning Open
Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse of the dimensionality and the exponential gro…
View article: S-OHEM: Stratified Online Hard Example Mining for Object Detection
S-OHEM: Stratified Online Hard Example Mining for Object Detection Open
One of the major challenges in object detection is to propose detectors with highly accurate localization of objects. The online sampling of high-loss region proposals (hard examples) uses the multitask loss with equal weight settings acro…