UFACTORY-Developer/tqc-XArm6Push-v3

This is a pre-trained model (TQC agent) for XArm6Push-v3 simulation task env, defined in here.

Hyperparameters:

OrderedDict([
    ('batch_size', 2048),
    ('buffer_size', 1000000),
    ('ent_coef', 'auto'),
    ('gamma', 0.95),
    ('learning_rate', 0.001),
    ('learning_starts', 100),
    ('policy', 'MultiInputPolicy'),
    ('policy_kwargs', dict(net_arch=[512, 512, 512], n_critics=2)),
    ('replay_buffer_class', HerReplayBuffer),
    ('replay_buffer_kwargs', dict( goal_selection_strategy='future', n_sampled_goal=4)),
    ('tau', 0.05)
])