Tag: adversarial reinforcement learning
Browse our exclusive articles!
SAVOIR: Shapley-Based Social Intelligence for AI Agents
Discover SAVOIR, a Shapley-based framework enhancing social intelligence in AI agents through fair reward attribution and improved dialogue learning.
ARES: Enhancing AI Safety with Adaptive Red-Teaming
Discover how ARES improves AI safety by adaptive red-teaming and repairing policy-reward systems in large language models.
UniDoc-RL: Advanced Visual RAG with Hierarchical Actions
UniDoc-RL enhances visual retrieval-augmented generation using hierarchical actions and dense rewards for superior reasoning in vision-language models.
Robust Policy Learning Against Adversaries with Regret Guarantees
Discover robust policy learning methods under adversarial conditions with regret and violation guarantees for safer AI decision-making systems.
EnvScaler: Scalable Tool-Interactive Environments for LLMs
EnvScaler automates scalable tool-interactive environments for LLM agents, enhancing multi-tool task training via programmatic synthesis.