Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
Building an agent that can mimic human behavior patterns to accomplish various open-world tasks is a long-term goal. To enable agents to effectively learn behavioral patterns across diverse tasks, a key challenge lies in modeling the intricate relationships among observations, actions, and language. To this end, we propose Optimus-2, a novel Minecraft agent that incorporates a Multimodal Large Language Model (MLLM) for high-level planning, alongside a Goal-Observation-Action Conditioned Policy (GOAP) for low-level control. GOAP contains (1) an Action-guided Behavior Encoder that models causal relationships between observations and actions at each timestep, then dynamically interacts with the historical observation-action sequence, consolidating it into fixed-length behavior tokens, and (2) an MLLM that aligns behavior tokens with open-ended language instructions to predict actions auto-regressively. Moreover, we introduce a high-quality Minecraft Goal-Observation-Action (MGOA)} dataset, which contains 25,000 videos across 8 atomic tasks, providing about 30M goal-observation-action pairs. The automated construction method, along with the MGOA dataset, can contribute to the community's efforts to train Minecraft agents. Extensive experimental results demonstrate that Optimus-2 exhibits superior performance across atomic tasks, long-horizon tasks, and open-ended instruction tasks in Minecraft.
Code (0)
등록된 구현이 없습니다.
Tasks
Large Language ModelMinecraftMultimodal Large Language ModelSimilar Papers 제목 키워드 기반
Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts
Recently, agents based on multimodal large language models (MLLMs) have achieved remarkable progress across various domains. However, building a generalist agent with capabilities such as perception, planning, action, gr…
DiversityMinecraftMixture-of-ExpertsMultimodal ReasoningOptimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
Building a general-purpose agent is a long-standing vision in the field of artificial intelligence. Existing agents have made remarkable progress in many domains, yet they still struggle to complete long-horizon tasks in…
AttributeIn-Context LearningMinecraftWorld KnowledgeJARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world…
MinecraftSTEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft
Recently, the STEVE-1 approach has been introduced as a method for training generative agents to follow instructions in the form of latent CLIP embeddings. In this work, we present a methodology to extend the control mod…
Decision MakingMinecraftSequential Decision MakingOmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produ…
DecoderImitation LearningInstruction FollowingMinecraft+2