๐ฎ 2048 RL Agent (W&B Serverless)
This agent was trained using W&B Serverless RL on CoreWeave infrastructure. It learned to play 2048 via reinforcement learning loops.
๐ Files
- adapter_model.safetensors: The trained LoRA weights.
- evaluation_script.py: Script to evaluate the agent.
๐ Usage
Check evaluation_script.py for inference details.