Aditya ✓

[text] If you’re trying to go deeper into Deep RL, LLMs, post-training, RL environments, or AI research, there’s one thing that gets harder to avoid: “Math” Not because you need to become a mathematician. Because math explains what the model is actually doing under the hood. 🧵

[text] Currently spending more time learning RL, especially around agents and RL environments. Would love to connect with people working in RL, agent training, environments, or related research. Always happy to learn from people building in this space. 🤝

[text] Ever wondered what actually happens when an AI learns? Understanding this loop matters when we want agents to improve toward specific goals. I’m going deeper into RL and trying to understand what happens under the hood. 🧵