@openpipe.bsky.social
Environment engineering is the next big thing in RL
April 18, 2025 at 11:33 PM
Environment engineering is the next big thing in RL
🧵 Excited to announce ART (Agent Reinforcement Trainer), a new RL framework for easily training agents with GRPO!
Optimized for best-in-class efficiency and agentic, multi-turn interactions.
Optimized for best-in-class efficiency and agentic, multi-turn interactions.
April 14, 2025 at 7:47 PM
🧵 Excited to announce ART (Agent Reinforcement Trainer), a new RL framework for easily training agents with GRPO!
Optimized for best-in-class efficiency and agentic, multi-turn interactions.
Optimized for best-in-class efficiency and agentic, multi-turn interactions.