38 lines
686 B
YAML
38 lines
686 B
YAML
|
# Example W&B sweep configuration. Customize the task, parameters, and
|
||
|
|
# search space for your own experiment.
|
||
|
|
#
|
||
|
|
# Usage:
|
||
|
|
# ./scripts/cloud/sweep-launch.sh A100:4
|
||
|
|
|
||
|
|
name: velocity-lr-entropy-sweep
|
||
|
|
project: mjlab
|
||
|
|
program: train
|
||
|
|
method: random
|
||
|
|
metric:
|
||
|
|
name: Train/mean_reward
|
||
|
|
goal: maximize
|
||
|
|
|
||
|
|
parameters:
|
||
|
|
agent.algorithm.learning-rate:
|
||
|
|
distribution: log_uniform_values
|
||
|
|
min: 1e-4
|
||
|
|
max: 1e-2
|
||
|
|
agent.algorithm.entropy-coef:
|
||
|
|
distribution: log_uniform_values
|
||
|
|
min: 0.001
|
||
|
|
max: 0.1
|
||
|
|
|
||
|
|
command:
|
||
|
|
- ${env}
|
||
|
|
- uv
|
||
|
|
- run
|
||
|
|
- ${program}
|
||
|
|
- Mjlab-Velocity-Flat-Unitree-G1
|
||
|
|
- --env.scene.num-envs
|
||
|
|
- "4096"
|
||
|
|
- --agent.max-iterations
|
||
|
|
- "6000"
|
||
|
|
- ${args}
|
||
|
|
|
||
|
|
run_cap: 8
|