D
Devendra Singh Chaplot
Researcher at Carnegie Mellon University
Publications - 48
Citations - 2501
Devendra Singh Chaplot is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 20, co-authored 47 publications receiving 1705 citations. Previous affiliations of Devendra Singh Chaplot include Facebook & Samsung.
Papers
More filters
Posted Content
On Evaluation of Embodied Navigation Agents
Peter Anderson,Angel X. Chang,Devendra Singh Chaplot,Alexey Dosovitskiy,Saurabh Gupta,Vladlen Koltun,Jana Kosecka,Jitendra Malik,Roozbeh Mottaghi,Manolis Savva,Amir Roshan Zamir +10 more
TL;DR: The present document summarizes the consensus recommendations of a working group to study empirical methodology in navigation research and discusses different problem statements and the role of generalization, present evaluation measures, and provides standard scenarios that can be used for benchmarking.
Proceedings Article
Learning to Explore using Active Neural SLAM
TL;DR: This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM', which leverages the strengths of both classical and learning-based methods, by using analytical path planners with learned SLAM module, and global and local policies.
Posted Content
Playing FPS Games with Deep Reinforcement Learning
TL;DR: This paper presents the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states, and substantially outperforms built-in AI agents of the game as well as humans in deathmatch scenarios.
Posted Content
Object Goal Navigation using Goal-Oriented Semantic Exploration
TL;DR: A modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category and outperforms a wide range of baselines including end-to-end learning-based methods as well as modular map- based methods.
Posted Content
Gated-Attention Architectures for Task-Oriented Language Grounding
Devendra Singh Chaplot,Kanthashree Mysore Sathyendra,Rama Kumar Pasumarthi,Dheeraj Rajagopal,Ruslan Salakhutdinov +4 more
TL;DR: This paper propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input.