AI2-THOR

AI2-THOR is a simulated environment that contains interactive 3D scenes used to evaluate the performance of AI systems in understanding and executing tasks involving complex object interactions.

Papers using AI2-THOR (9)

LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner2024 · 1 citesLLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments2024 · 1 citesScale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams2026GRIP: A Unified Framework For Grid-based Relay And Co-occurrence-aware Planning In Dynamic Environments2025Lamma-p: Generalizable Multi-agent Long-horizon Task Allocation And Planning With Lm-driven PDDL Planner2024 · 10 citesLota-bench: Benchmarking Language-oriented Task Planners For Embodied Agents2024VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation2019 · 3 citesMatching options to tasks using Option-Indexed Hierarchical Reinforcement Learning2022LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents2024