Mapping Instructions and Visual Observations to Actions with Reinforcement Learning
We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network agent. To guide the agent's exploration, we use reward shaping with different forms of supervision. Our approach does not require intermediate representations, planning procedures, or training different models. We evaluate in a simulated environment, and show significant improvements over supervised learning and common reinforcement learning variants.
Code (1)
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction
We propose to decompose instruction execution to goal prediction and action generation. We design a model that maps raw visual observations to goals using LINGUNET, a language-conditioned image generation network, and th…
Action GenerationConditional Image GenerationImage GenerationInstruction FollowingLarge Language Models as Generalizable Policies for Embodied Tasks
We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained froze…
Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+1Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation
We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of…
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the a…
continuous-controlContinuous ControlImitation LearningInstruction Following+1Instruction-Following Agents with Multimodal Transformer
Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure …
Instruction FollowingVisual Grounding