InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model
Model-based Reinforcement Learning (MBRL) has emerged as a promising paradigm for autonomous driving, where data efficiency and robustness are critical. Yet, existing solutions often rely on carefully crafted, task specific extrinsic rewards, limiting generalization to new tasks or environments. In this paper, we propose InDRiVE (Intrinsic Disagreement based Reinforcement for Vehicle Exploration), a method that leverages purely intrinsic, disagreement based rewards within a Dreamer based MBRL framework. By training an ensemble of world models, the agent actively explores high uncertainty regions of environments without any task specific feedback. This approach yields a task agnostic latent representation, allowing for rapid zero shot or few shot fine tuning on downstream driving tasks such as lane following and collision avoidance. Experimental results in both seen and unseen environments demonstrate that InDRiVE achieves higher success rates and fewer infractions compared to DreamerV2 and DreamerV3 baselines despite using significantly fewer training steps. Our findings highlight the effectiveness of purely intrinsic exploration for learning robust vehicle control behaviors, paving the way for more scalable and adaptable autonomous driving systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingCollision AvoidanceModel-based Reinforcement LearningSimilar Papers 제목 키워드 기반
InDRiVE: Reward-Free World-Model Pretraining for Autonomous Driving via Latent Disagreement
Model-based reinforcement learning (MBRL) can reduce interaction cost for autonomous driving by learning a predictive world model, but it typically still depends on task-specific rewards that are difficult to design and …
Reinforcement LearningCollision AvoidanceAutonomous DrivingReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation
We present ReinDriveGen, a framework that enables full controllability over dynamic driving scenes, allowing users to freely edit actor trajectories to simulate safety-critical corner cases such as front-vehicle collisio…
Scene GenerationReward Uncertainty for Exploration in Preference-based Reinforcement Learning
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by ac…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot ManipulationEpistemic Uncertainty for Test-Time Discovery
Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar…
Reinforcement LearningSelf-Supervised Exploration via Disagreement
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulatio…
Active LearningEfficient ExplorationMuJoCoReinforcement Learning+2