Multi-Agent System
A Unified Diversity Measure for Multiagent Reinforcement Learning
Download Abstract: Promoting behavioural diversity is of critical importance in multi-agent reinforcement learning, since it helps the agent population maintain robust performance when encountering unfamiliar opponents at test time, or, when the game is highly non-transitive in the strategy space (e.g., Rock-Paper-Scissor). While a myriad of diversity metrics have been proposed, there are no widely …
A Unified Diversity Measure for Multiagent Reinforcement Learning Read More »
Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
Download Abstract: This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds. Traditional fixed-viewpoint multi-camera solutions for human motion capture (MoCap) are limited in capture space and susceptible to dynamic occlusions. Active camera approaches proactively control camera poses to find optimal viewpoints for …
Proactive Multi-Camera Collaboration for 3D Human Pose Estimation Read More »
Multi-Agent Reinforcement Learning is A Sequence Modeling Problem
Download Abstract: Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract multi-agent decision making into an SM problem and benefit from the prosperous development of SMs. In this paper, we introduce …
Multi-Agent Reinforcement Learning is A Sequence Modeling Problem Read More »
Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning
Download Abstract: Setting up a well-designed reward function has been challenging for many reinforcement learning applications. Preference-based reinforcement learning (PbRL) provides a new framework that avoids reward engineering by leveraging human preferences (i.e., preferring apples over oranges) as the reward signal. Therefore, improving the efficacy of data usage for preference data becomes critical. In this …
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
Download Abstract: Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations. In this paper, we develop a unified framework that describes variations of GMRL algorithms and points out that existing stochastic meta-gradient estimators adopted by GMRL are actually textbf{biased}. …
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning Read More »