====== Agent Simulation Environments ======

Agent simulation environments are 3D platforms designed for training and evaluating embodied AI agents in realistic settings. Platforms like **SimWorld**, **AI2-THOR**, and **Habitat** provide photo-realistic visuals, physics simulations, and programmatic APIs that enable agents to learn navigation, object manipulation, and multi-step task completion through interaction rather than static datasets.

===== Overview =====

Training AI agents for real-world tasks is expensive and risky in physical environments. Simulation environments provide a scalable alternative: agents can fail safely, train on millions of episodes, and transfer learned skills to real robots. The key challenge is building environments rich enough that skills transfer from simulation to reality (sim2real transfer).

===== AI2-THOR =====

**AI2-THOR** (The House Of inteRactions), developed by the **Allen Institute for AI**, is an interactive 3D environment built on Unity3D with NVIDIA PhysX for physics simulation. It provides the richest object interaction model among major simulators.

Key features:

  * **Photo-realistic indoor scenes** via iTHOR (curated rooms), RoboTHOR (real-apartment replicas), and ProcTHOR-10K (procedurally generated scenes)
  * **Rich object interactions** - Actionable properties for pickup, manipulation, opening, toggling, cooking, and cleaning
  * **Multi-modal observations** - RGB images, depth maps, semantic segmentation, instance masks
  * **Multi-agent support** via DualTHOR for cooperative/competitive scenarios
  * **Extensible architecture** - Client-server design allows custom scenes and objects

ProcTHOR-10K enables generating infinite procedural scenes, achieving state-of-the-art on multiple navigation benchmarks without human supervision.

===== Habitat =====

**Habitat**, developed by **Meta AI Research**, prioritizes simulation speed for large-scale reinforcement learning. It achieves thousands of frames per second per thread -- orders of magnitude faster than AI2-THOR.

Key features:

  * **High-speed rendering** - Enables massive parallelism for RL training
  * **Habitat 2.0** - Adds object manipulation with physics-based forces and torques (92 interactive object states)
  * **Standardized tasks** - PointNav (navigate to coordinates), ObjectNav (find objects), and home assistant training
  * **Habitat Challenge** - Annual competition driving progress on embodied AI tasks

Habitat differs from AI2-THOR in its interaction model: it uses physics-based forces rather than predefined action primitives, providing more realistic but less structured manipulation.

===== SimWorld =====

**SimWorld** is a newer platform emphasizing **open-ended world generation** beyond the fixed or procedurally templated scenes of AI2-THOR and Habitat. It targets general-purpose agent training in diverse, dynamic environments.

Key differentiators:

  * **Open-ended generation** - Creates diverse environments without scene templates
  * **High scalability** - Designed for generating varied training scenarios at scale
  * **Broader domain coverage** - Extends beyond indoor scenes to diverse settings

<code python>
# Example: Setting up an AI2-THOR navigation task
import ai2thor.controller

controller = ai2thor.controller.Controller(
    scene="FloorPlan1",
    gridSize=0.25,
    renderDepthImage=True,
    renderInstanceSegmentation=True
)

# Agent navigates to find a target object
event = controller.step(action="MoveAhead")
rgb_frame = event.frame           # (H, W, 3) RGB image
depth_frame = event.depth_frame   # (H, W) depth map

# Rich object interactions
controller.step(action="PickupObject", objectId="Mug|0.25|1.0|0.5")
controller.step(action="OpenObject", objectId="Fridge|2.0|0.5|1.0")
controller.step(action="PutObject", objectId="Fridge|2.0|0.5|1.0")

# Check task completion
objects = event.metadata["objects"]
mug_in_fridge = any(
    o["objectId"].startswith("Mug") and o["parentReceptacles"] 
    and "Fridge" in str(o["parentReceptacles"])
    for o in objects
)
</code>

===== Comparison =====

^ Feature ^ AI2-THOR ^ Habitat ^ SimWorld ^
| **Speed** | Tens of FPS | Thousands of FPS | High (varies) |
| **Interactions** | Rich predefined actions | Physics-based forces | Open-ended |
| **Scene generation** | ProcTHOR procedural | Fixed scan datasets | Open-ended generation |
| **Primary strength** | Object manipulation | Navigation at scale | Environment diversity |
| **Physics engine** | NVIDIA PhysX | Bullet Physics | Custom |

===== Applications =====

  * **Robot skill learning** - Pre-training manipulation and navigation policies before real-world deployment
  * **Vision-language grounding** - Training agents to follow natural language instructions in visual environments
  * **Multi-agent coordination** - Cooperative and competitive scenarios in shared environments
  * **Benchmark evaluation** - Standardized tasks for measuring agent progress (ObjectNav, Rearrangement)

===== References =====

  * [[https://ai2thor.allenai.org|AI2-THOR Official Site]]
  * [[https://ai2thor.allenai.org/publications/|AI2-THOR Publications]]
  * [[https://aihabitat.org|Habitat Official Site]]
  * [[https://ai.meta.com/blog/habitat-20-training-home-assistant-robots-with-faster-simulation-and-new-benchmarks/|Meta AI - Habitat 2.0]]
  * [[https://simworld.org/assets/white_paper.pdf|SimWorld White Paper]]
  * [[https://arxiv.org/html/2512.01078v2|Simulation Environment Design Comparison]]

===== See Also =====

  * [[computer_use_benchmark]] - GUI interaction benchmarks (2D counterpart)
  * [[terminal_bench]] - CLI agent benchmark in sandboxed environments
  * [[strategy_guided_exploration]] - RL exploration strategies for agent training
  * [[gaia_benchmark]] - Real-world task benchmark for AI assistants