<ul data-eligibleForWebStory="false"><li>Researchers have developed a novel method for knowledge transfer in model-based reinforcement learning to address constraints of large world models in resource-limited environments.</li><li>Their technique efficiently distills a multi-task agent with 317M parameters into a compact model with 1M parameters, leading to improved performance on diverse tasks.</li><li>The distilled model achieved a state-of-the-art normalized score of 28.45, surpassing the original 1M parameter model score of 18.93, showcasing the effectiveness of the distillation process.</li><li>The researchers further optimized the distilled model through post-training quantization, reducing its size by approximately 50%, aiming to address practical deployment challenges in multi-task reinforcement learning systems.</li></ul>

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

Discover more