Command:
./scripts/train_himloco_isaaclab_him.sh --num_envs 64 --max_iterations 2

Runtime:
GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, sm_120
Torch: 2.7.0+cu128
Isaac Sim: 5.1
rsl-rl-lib: 3.0.1

Key environment shapes:
Policy observation: 270 = 45 x 6
Critic observation: 238 = 45 + 3 + 3 + 187
Action: 12
Actor input: 64 = 45 + 3 + 16
Estimator input: 270

Iteration 0/2:
Computation: 2630 steps/s
Mean value_function loss: 0.3333
Mean surrogate loss: 0.0228
Mean entropy loss: 17.0127
Mean estimation loss: 0.7230
Mean swap loss: 0.1080
Mean reward: -2.80
Mean episode length: 68.71
Total timesteps: 6400
Iteration time: 2.43s

Iteration 1/2:
Computation: 4110 steps/s
Mean value_function loss: 0.1658
Mean surrogate loss: -0.0045
Mean entropy loss: 17.0122
Mean estimation loss: 0.6086
Mean swap loss: 0.1079
Mean reward: -3.24
Mean episode length: 83.98
Total timesteps: 12800
Iteration time: 1.56s

Training time: 4.21 seconds