Unsupervised Object-Based Transition Models for 3D Partially Observable Environments
We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames. The model is trained end-to-end without supervision using losses at the level of the object-structured representation rather than pixels. Thanks to its alignment module, the model deals properly with two issues that are not handled satisfactorily by other transition models, namely object persistence and object identity. We show that the combination of an object-level loss and correct object alignment over time enables the model to outperform a state-of-the-art baseline, and allows it to deal well with object occlusion and re-appearance in partially observable environments.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSimilar Papers 제목 키워드 기반
Context Discovery for Model Learning in Partially Observable Environments
The ability to learn a model is essential for the success of autonomous agents. Unfortunately, learning a model is difficult in partially observable environments, where latent environmental factors influence what the age…
Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment
Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system's …
Decision MakingState EstimationInferring Reward Machines and Transition Machines from Partially Observable Markov Decision Processes
Partially Observable Markov Decision Processes (POMDPs) are fundamental to many real-world applications. Although reinforcement learning (RL) has shown success in fully observable domains, learning policies from traces i…
Reinforcement LearningFuture Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments
Learning a good history representation is one of the core challenges of reinforcement learning (RL) in partially observable environments. Recent works have shown the advantages of various auxiliary tasks for facilitating…
Future predictionMemorizationPredictionreinforcement-learning+3Decision Making for Autonomous Vehicles
This paper is on decision making of autonomous vehicles for handling roundabouts. The round intersection is introduced first followed by the Markov Decision Processes (MDP), the Partially Observable Markov Decision Proce…
Autonomous VehiclesDecision Making