Environment catalog

Long-horizon constraint placement against a deterministic explorer with private targets.

• Treant's Forest ↗

Schedule low-cost bonds among moving components on a toroidal plane.

• Molecules ↗

Five hundred turns of hierarchical machine investment and compounding production.

• Apple Incremental Game ↗

Full-range warehouse storage and retrieval through a compact forklift instruction language.

• Warehouseman ↗

Small state-space control tasks with discrete or scalar continuous Actions.

• CartPole ↗
• Acrobot
• Mountain Car
• Continuous Mountain Car
• Pendulum

Rule-based discrete tasks for planning, stochastic transitions, and delayed reward.

• Blackjack
• CliffWalking
• FrozenLake
• Taxi

Landing, locomotion, and visual driving in medium-weight physics environments.

• LunarLander
• BipedalWalker
• CarRacing

Continuous control from small arms and pendulums to contact-rich locomotion.

• Reacher
• Pusher
• InvertedPendulum
• InvertedDoublePendulum
• Swimmer
• Hopper
• +5 more

Canonical state-based continuous-control tasks from balancing and locomotion to manipulation.

• Acrobot / Cartpole / Pendulum
• Ball in Cup / Finger
• Cheetah / Hopper / Walker
• Fish / Swimmer
• Humanoid
• Manipulator / Point Mass / Reacher

Partially observable navigation, memory, object interaction, and procedural layouts.

• DoorKey
• KeyCorridor
• Memory
• Fetch
• MultiRoom
• DynamicObstacles
• +15 more

Wave Function Collapse layouts spanning mazes, rooms, dungeons, obstacles, and caves.

• Maze
• Rooms
• Dungeon
• Obstacles
• Skew
• 22 presets total

Language-conditioned instruction following from atomic navigation to composite missions.

• GoTo
• Open
• PickupPut
• Unlock
• Composite
• 40 tasks total

Structured combinatorial environments with exact action masks and task-specific progress diagnostics.

• 2048 / Graph Coloring / Minesweeper
• Rubik's Cube / Sudoku / Sliding Tile
• BinPack / FlatPack / Knapsack
• JobShop / Tetris
• CVRP / TSP / Maze
• Snake / PacMan

Goal-conditioned reaching, manipulation, maze, dexterous hand, and kitchen tasks.

• Fetch
• Point / Ant Maze
• Adroit Hand
• Shadow Hand
• FrankaKitchen

Single-task and multi-task robotic manipulation collections.

• MT1
• MT10
• MT50
• Custom collections

Single- and dual-arm Panda manipulation with dense task state and per-Episode visual evidence.

• Lift / Stack
• NutAssembly
• PickPlace
• Door / Wipe / ToolHang
• TwoArmLift / TwoArmPegInHole
• TwoArmHandover / TwoArmTransport

Traffic negotiation, parking, racing, and lane keeping.

• Highway
• Merge
• Roundabout
• Intersection
• TwoWay
• Exit
• +4 more

Open-world survival, resource collection, crafting, and long-horizon development from RGB observations.

• Canonical achievement score
• Long-horizon development
• Survival development

Interactive visual reasoning across complete games, in-Episode level resets, and official scorecard aggregation.

• 25 version-pinned public games
• Custom fixed collections

Long-horizon procedural dungeon survival with complete semantic training trajectories.

• NetHackScore-v0 ↗

Arcade control using the redistributable Tetris ROM.

• Tetris-v5

First-person navigation and combat across the standard packaged scenarios.

• Basic
• DeadlyCorridor
• Deathmatch
• HealthGathering
• MyWayHome
• TakeCover
• +1 more

Genesis arcade control from the packaged Level 1 state.

• Airstriker-Genesis-v0

Long-horizon deckbuilding with hands, shops, Jokers, consumables, packs, and antes.

• Red Deck · White Stake