trainer_type: sac
hyperparameters:
learning_rate: 0.0003
learning_rate_schedule: constant
learning_rate_schedule: linear
batch_size: 64
buffer_size: 500000
buffer_init_steps: 0
time_horizon: 1000
summary_freq: 12000
threaded: true
load_model: false
load_encoder: true
train_encoder: false
load_action: true
train_action: false
transfer_path: "results/ball-s0/3DBall"
transfer_path: "results/mass-s0/3DBall"
network_settings:
normalize: true
hidden_units: 128
parameter_randomization:
mass:
sampler_type: uniform
sampler_parameters:
min_value: 2.0
max_value: 2.0
# parameter_randomization:
# mass:
# sampler_type: uniform
# sampler_parameters:
# min_value: 2.0
# max_value: 2.0
transfer_path: "results/ball-s1/3DBall"
transfer_path: "results/mass-s1/3DBall"
transfer_path: "results/ball-s2/3DBall"
transfer_path: "results/mass-s2/3DBall"
transfer_path: "results/ball-s3/3DBall"
transfer_path: "results/mass-s3/3DBall"
transfer_path: "results/ball-s4/3DBall"
transfer_path: "results/mass-s4/3DBall"