dummy_config.yaml

algorithm:
  class_name: PPO
  # training parameters
  # -- value function
  value_loss_coef: 1.0
  clip_param: 0.2
  use_clipped_value_loss: true
  # -- surrogate loss
  desired_kl: 0.01
  entropy_coef: 0.01
  gamma: 0.99
  lam: 0.95
  max_grad_norm: 1.0
  # -- training
  learning_rate: 0.001
  num_learning_epochs: 5
  num_mini_batches: 4  # mini batch size = num_envs * num_steps / num_mini_batches
  schedule: adaptive  # adaptive, fixed

  # -- Random Network Distillation
  rnd_cfg:
      weight: 0.0  # initial weight of the RND reward

      # note: This is a dictionary with a required key called "mode" which can be one of "constant" or "step".
      #   - If "constant", then the weight is constant.
      #   - If "step", then the weight is updated using the step scheduler. The dictionary should contain additional parameters:
      #     - max_num_steps: maximum number of steps to update the weight
      #     - final_value: final value of the weight
      # If None, then no scheduler is used.
      weight_schedule: null

      reward_normalization: false  # whether to normalize RND reward
      gate_normalization: true  # whether to normalize RND gate observations

      # -- Learning parameters
      learning_rate: 0.001  # learning rate for RND

      # -- Network parameters
      # note: if -1, then the network will use dimensions of the observation
      num_outputs: 1  # number of outputs of RND network
      predictor_hidden_dims: [-1] # hidden dimensions of predictor network
      target_hidden_dims: [-1]  # hidden dimensions of target network

  # -- Symmetry Augmentation
  symmetry_cfg:
    use_data_augmentation: true  # this adds symmetric trajectories to the batch
    use_mirror_loss: false  # this adds symmetry loss term to the loss function

    # string containing the module and function name to import.
    # Example: "legged_gym.envs.locomotion.anymal_c.symmetry:get_symmetric_states"
    #
    # .. code-block:: python
    #
    #     @torch.no_grad()
    #     def get_symmetric_states(
    #        obs: Optional[torch.Tensor] = None, actions: Optional[torch.Tensor] = None, cfg: "BaseEnvCfg" = None, is_critic: bool = False,
    #     ) -> Tuple[torch.Tensor, torch.Tensor]:
    #
    data_augmentation_func: null

    # coefficient for symmetry loss term
    # if 0, then no symmetry loss is used
    mirror_loss_coeff: 0.0

policy:
  class_name: ActorCritic
  # for MLP i.e. `ActorCritic`
  activation: elu
  actor_hidden_dims: [128, 128, 128]
  critic_hidden_dims: [128, 128, 128]
  init_noise_std: 1.0
  # only needed for `ActorCriticRecurrent`
  # rnn_type: 'lstm'
  # rnn_hidden_size: 512
  # rnn_num_layers: 1

runner:
    num_steps_per_env: 24  # number of steps per environment per iteration
    max_iterations: 1500  # number of policy updates
    empirical_normalization: false
    # -- logging parameters
    save_interval: 50  # check for potential saves every `save_interval` iterations
    experiment_name: walking_experiment
    run_name: ""
    # -- logging writer
    logger: tensorboard  # tensorboard, neptune, wandb
    neptune_project: legged_gym
    wandb_project: legged_gym
    # -- load and resuming
    resume: false
    load_run: -1  # -1 means load latest run
    resume_path: null  # updated from load_run and checkpoint
    checkpoint: -1  # -1 means load latest checkpoint

runner_class_name: OnPolicyRunner
seed: 1