Agents That Listen: High-throughput Reinforcement Learning With Multiple Sensory Systems

Abstract

Humans and other intelligent animals evolved highly sophisticated perception systems that combine multiple sensory modalities. On the other hand, state-of-the-art artificial agents rely mostly on visual inputs or structured low-dimensional observations provided by instrumented environments. Learning to act based on combined visual and auditory inputs is still a new topic of research that has not been explored beyond simple scenarios. To facilitate progress in this area we introduce a new version of VizDoom simulator to create a highly efficient learning environment that provides raw audio observations. We study the performance of different model architectures in a series of tasks that require the agent to recognize sounds and execute instructions given in natural language. Finally, we train our agent to play the full game of Doom and find that it can consistently defeat a traditional vision-based adversary. We are currently in the process of merging the augmented simulator with the mai

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keyhegde2021agents

Related papers

• Deep Reinforcement Learning For Doom Using Unsupervised Auxiliary Tasks (2018)0.00
• Enhancing Vision-language Model Training With Reinforcement Learning In Synthetic Worlds For Real-world Success (2025)0.00
• Vizdoom: DRQN With Prioritized Experience Replay, Double-q Learning, & Snapshot Ensembling (2018)8.60
• Autoencoder-augmented Neuroevolution For Visual Doom Playing (2017)11.49
• Explore, Exploit Or Listen: Combining Human Feedback And Policy Model To Speed Up Deep Reinforcement Learning In 3D Worlds (2017)0.00
• Playing Games In The Dark: An Approach For Cross-modality Transfer In Reinforcement Learning (2019)0.00
• Vizdoom Competitions: Playing Doom From Pixels (2018)13.79
• How To Sense The World: Leveraging Hierarchy In Multimodal Perception For Robust Reinforcement Learning Agents (2021)0.00