Learning and Planning with a Semantic Model

2018/09/28 by Yi Wu, Wu, Yi, Yuxin Wu +9 · 1 voice
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.AI #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1809.10842

Abstract

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid model-based and model-free approach, LEArning and Planning with Semantics (LEAPS), consisting of a multi-target sub-policy that acts on visual inputs, and a Bayesian model over semantic structures. When placed in an unseen environment, the agent plans with the semantic model to make high-level decisions, proposes the next sub-target for the sub-policy to execute, and updates the semantic model based on new observations. We perform experiments in visual navigation tasks using House3D, a 3D environment that contains diverse human-designed indoor scenes with real-world objects. LEAPS outperforms strong baselines that do not explicitly plan using the semantic content.

Discussions

• Learning and Planning with a Semantic Model [hn, 2 points, 0 comments]

Related

• Visual Semantic Planning using Deep Successor Representations
• Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
• SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments
• Vision-Language Models Provide Promptable Representations for Reinforcement Learning
• Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation