Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior
In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectories that distinguish between four distinct classes of driver behavior. Such encodings are learned without any knowledge of the number of driver classes or any objective that directly requires the models to learn encodings for each class. We show that driving policies trained with knowledge of latent variables are more effective than baseline methods at imitating the driver behavior that they are trained to replicate. Furthermore, we demonstrate that the actions chosen by our policy are heavily influenced by the latent variable settings that are provided to them.
Code (2)
Similar Papers 제목 키워드 기반
Imitating Latent Policies from Observation
In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observation…
Imitation LearningDeconfounding Imitation Learning with Variational Inference
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In pr…
Imitation LearningVariational InferenceBeyond Imitation: Reinforcement Learning for Active Latent Planning
Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume …
Reinforcement LearningLearning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviors
We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our …
DecoderBrain-Inspired Inference on Missing Video Sequence
In this paper, we propose a novel end-to-end architecture that could generate a variety of plausible video sequences correlating two given discontinuous frames. Our work is inspired by the human ability of inference. Spe…