Voyager: An Open-Ended Embodied Agent with Large Language Models
Explore this paper's citation graph
- Type
- preprint
- Published
- 2023-05-25
- Cited by
- 2,202
- References
- 89
- Access
- Open access
- OpenAlex
- https://openalex.org/W4378505261
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:258887849
Keywords
Codebase, Computer science, Executable, Embodied cognition, Context (archaeology)
References
- Playing Atari with Deep Reinforcement Learning
- Reinforcement learning in robotics: A survey
- The Malmo Platform for Artificial Intelligence Experimentation
- Proximal Policy Optimization Algorithms
- Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
- A Brief Survey of Deep Reinforcement Learning
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
- Continual Lifelong Learning with Neural Networks: A Review
- Diversity is All You Need: Learning Skills without a Reward Function
- Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multiobjective Evolutionary Algorithm
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- Execution-Guided Neural Program Synthesis
- Go-Explore: a New Approach for Hard-Exploration Problems
- Habitat: A Platform for Embodied AI Research
- Write, Execute, Assess: Program Synthesis with a REPL
- MineRL: A Large-Scale Dataset of Minecraft Demonstrations
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Recent Advances in Robot Learning from Demonstration
- Program Guided Agent
Cited by
- VIMA: General Robot Manipulation with Multimodal Prompts
- A Survey on Transformers in Reinforcement Learning
- Mastering Diverse Domains through World Models
- Reinforcement Learning Friendly Vision-Language Model for Minecraft
- ZeroFlow: Scalable Scene Flow via Distillation
- Large Language Models as Tool Makers
- Language Models are Pragmatic Speakers
- Grammar Prompting for Domain-Specific Language Generation with Large Language Models
- ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing
- AutoScrum: Automating Project Planning Using Large Language Models
- Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
- Large Language Models Are Semi-Parametric Reinforcement Learning Agents
- ChessGPT: Bridging Policy Learning and Language Modeling
- Artificial Intelligence Regulation, Minimum Viable Products, and Partitive Innovation
- Supervised Pretraining Can Learn In-Context Reinforcement Learning
- Building Cooperative Embodied Agents Modularly with Large Language Models
- Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models
- Large Language Models as General Pattern Machines
- Demonstrations of the Potential of AI-based Political Issue Polling
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
Related papers
- Extracting executable transformations from distilled code changes
- Literate Program Execution for Teaching Computational Science
- Similarity Calculation of Executable Using Intel Pin Instrumentation Framework
- Automatically Recommending Peer Reviewers in Modern Code Review
- Research on the Collaborative Analysis Technology for Source Code and Binary Executable Based upon the Unified Defect Mode Set
- Measuring Method of Worst-case Execution Time by Analyzing Relation between Source Code and Executable Code
- Automatic mining of source code repositories to improve bug finding techniques
- An empirical study of build maintenance effort