ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI

Documenti analoghi

• GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
  di: Khanna, Mukul, et al.
  Pubblicazione: (2024)
• EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device
  di: Chhablani, Gunjan, et al.
  Pubblicazione: (2025)
• Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
  di: Gupta, Gunshi, et al.
  Pubblicazione: (2025)
• Seeing the Unseen: Visual Common Sense for Semantic Placement
  di: Ramrakhya, Ram, et al.
  Pubblicazione: (2024)
• Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning
  di: Ramrakhya, Ram, et al.
  Pubblicazione: (2025)