I have been following along with the “Making a New Learning Environment” documentation tutorial at - ml-agents/docs/Learning-Environment-Create-New.md at release_18_docs · Unity-Technologies/ml-agents · GitHub
I get close to the end - the step where I enter the command:
mlagents-learn path/rollerball_config.yaml --run-id=RollerBall
I get the error:
mlagents.trainers.exception.TrainerConfigError: The option behaviors was specified in your YAML file, but is invalid.
Which I find a little odd due to the “
” symbols, like it can’t say exactly which option it doesn’t like.
I am using the file contents given in the tutorial’s YAML file:
behaviors:
RollerBall:
trainer_type: ppo
hyperparameters:
batch_size: 10
buffer_size: 100
learning_rate: 3.0e-4
beta: 5.0e-4
epsilon: 0.2
lambd: 0.99
num_epoch: 3
learning_rate_schedule: linear
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
reward_signals:
extrinsic:
gamma: 0.99
strength: 1.0
max_steps: 500000
time_horizon: 64
summary_freq: 10000
Can anyone point me in the right direction or have any ideas on what I can try next?