TransDreamerV3: Implanting Transformer In DreamerV3
This work addresses performance limitations in world model-based reinforcement learning for complex environments, though it is incremental with noted issues in tasks like Minecraft.
The paper tackles improving memory and decision-making in reinforcement learning by integrating a transformer encoder into the DreamerV3 architecture, resulting in enhanced performance on tasks like Atari-Freeway and Crafter compared to DreamerV3.
This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder. The model is designed to improve memory and decision-making capabilities in complex environments. We conducted experiments on Atari-Boxing, Atari-Freeway, Atari-Pong, and Crafter tasks, where TransDreamerV3 demonstrated improved performance over DreamerV3, particularly in the Atari-Freeway and Crafter tasks. While issues in the Minecraft task and limited training across all tasks were noted, TransDreamerV3 displays advancement in world model-based reinforcement learning, leveraging transformer architectures.