Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments
Training intelligent agents to navigate highly interactive environments presents significant challenges. While guided meta reinforcement learning (RL) approach that first trains a guiding policy to train the ego agent has proven effective in improving generalizability across scenarios with various levels of interaction, the state-of-the-art method tends to be overly sensitive to extreme cases, impairing the agents' performance in the more common scenarios. This study introduces a novel training framework that integrates guided meta RL with importance sampling (IS) to optimize training distributions iteratively for navigating highly interactive driving scenarios, such as T-intersections or roundabouts. Unlike traditional methods that may underrepresent critical interactions or overemphasize extreme cases during training, our approach strategically adjusts the training distribution towards more challenging driving behaviors using IS proposal distributions and applies the importance ratio to de-bias the result. By estimating a naturalistic distribution from real-world datasets and employing a mixture model for iterative training refinements, the framework ensures a balanced focus across common and extreme driving scenarios. Experiments conducted with both synthetic and naturalistic datasets demonstrate both accelerated training and performance improvements under highly interactive driving tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta Reinforcement LearningNavigateReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Feature Importance Guided Random Forest Learning with Simulated Annealing Based Hyperparameter Tuning
This paper introduces a novel framework for enhancing Random Forest classifiers by integrating probabilistic feature sampling and hyperparameter tuning via Simulated Annealing. The proposed framework exhibits substantial…
Feature ImportanceAnomaly DetectionThe Importance of Sampling inMeta-Reinforcement Learning
We interpret meta-reinforcement learning as the problem of learning how to quickly find a good sampling distribution in a new environment. This interpretation leads to the development of two new meta-reinforcement learni…
Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)HeteroSample: Meta-path Guided Sampling for Heterogeneous Graph Representation Learning
The rapid expansion of Internet of Things (IoT) has resulted in vast, heterogeneous graphs that capture complex interactions among devices, sensors, and systems. Efficient analysis of these graphs is critical for derivin…
Computational EfficiencyGraph Representation LearningLink PredictionNode Classification+1Robust Meta-Reinforcement Learning with Curriculum-Based Task Sampling
Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has bee…
Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Test-time reward-guided alignment of language models by importance sampling on pre-logit space
Test-time alignment of large language models (LLMs) attracts attention because fine-tuning of LLMs requires high computational costs. In this paper, we propose a new test-time reward-guided alignment method called adapti…