Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback explores Developing robust algorithms for multi-agent reinforcement learning in the presence of corrupted human feedback data.. Commercial viability score: 3/10 in Multi-Agent Reinforcement Learning.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisA Recipe for Stable Offline Multi-agent Reinforcement LearningViability: 1.0
- Builds On ThisAgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM AgentsViability: 2.0
- Prior WorkRobust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed NoiseViability: 3.0
- Prior WorkOffline Constrained RLHF with Multiple Preference OraclesViability: 3.0
- Prior WorkLearning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling
Related Resources
- Multi-Agent Reinforcement Learning(glossary)