MuJoCo environments
MuJoCo environments require the mujoco feature and MuJoCo 3.10.0. Construct them with new(None) for defaults or new(Some(config)). Actions and observations are DVector<f64>; control length is the loaded model’s nu, and controls use its actuator ranges.
| Environment | Default observation | Default action and range | Horizon |
|---|---|---|---|
| Ant | 105 | 8 × \([-1,1]\) | 1000 |
| HalfCheetah | 17 | 6 × \([-1,1]\) | 1000 |
| Hopper | 11 | 3 × \([-1,1]\) | 1000 |
| Humanoid | 348 | 17 × \([-0.4,0.4]\) | 1000 |
| HumanoidStandup | 348 | 17 × \([-0.4,0.4]\) | 1000 |
| InvertedDoublePendulum | 9 | 1 × \([-1,1]\) | 1000 |
| InvertedPendulum | 4 | 1 × \([-3,3]\) | 1000 |
| Pusher | 23 | 7 × \([-2,2]\) | 100 |
| Reacher | 10 | 2 × \([-1,1]\) | 50 |
| Swimmer | 8 | 2 × \([-1,1]\) | 1000 |
| Walker2d | 17 | 6 × \([-1,1]\) | 1000 |
Each action is held for frame_skip MuJoCo steps. Thus \(\Delta t=\text{frame_skip}\times\text{model timestep}\), and velocity rewards use displacement divided by this agent timestep. See backend dynamics.
Custom XML may change
nq,nv,nu, body count, ranges, timestep, and therefore observation/action dimensions. It must preserve body and site names used by task-specific lookups.