mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
60d4d5e1aa
* Remove all __future__ imports from RLlib. * Remove (object) again from tf_run_builder.py::TFRunBuilder. * Fix 2xLINT warnings. * Fix broken appo_policy import (must be appo_tf_policy) * Remove future imports from all other ray files (not just RLlib). * Remove future imports from all other ray files (not just RLlib). * Remove future import blocks that contain `unicode_literals` as well. Revert appo_tf_policy.py to appo_policy.py (belongs to another PR). * Add two empty lines before Schedule class. * Put back __future__ imports into determine_tests_to_run.py. Fails otherwise on a py2/print related error.
39 lines
1.4 KiB
Python
39 lines
1.4 KiB
Python
from ray.rllib.models.preprocessors import get_preprocessor
|
|
from ray.rllib.models.torch.torch_modelv2 import TorchModelV2
|
|
from ray.rllib.utils.annotations import override
|
|
from ray.rllib.utils import try_import_torch
|
|
|
|
torch, nn = try_import_torch()
|
|
F = nn.functional
|
|
|
|
|
|
class RNNModel(TorchModelV2, nn.Module):
|
|
"""The default RNN model for QMIX."""
|
|
|
|
def __init__(self, obs_space, action_space, num_outputs, model_config,
|
|
name):
|
|
TorchModelV2.__init__(self, obs_space, action_space, num_outputs,
|
|
model_config, name)
|
|
nn.Module.__init__(self)
|
|
self.obs_size = _get_size(obs_space)
|
|
self.rnn_hidden_dim = model_config["lstm_cell_size"]
|
|
self.fc1 = nn.Linear(self.obs_size, self.rnn_hidden_dim)
|
|
self.rnn = nn.GRUCell(self.rnn_hidden_dim, self.rnn_hidden_dim)
|
|
self.fc2 = nn.Linear(self.rnn_hidden_dim, num_outputs)
|
|
|
|
@override(TorchModelV2)
|
|
def get_initial_state(self):
|
|
# make hidden states on same device as model
|
|
return [self.fc1.weight.new(1, self.rnn_hidden_dim).zero_().squeeze(0)]
|
|
|
|
@override(TorchModelV2)
|
|
def forward(self, input_dict, hidden_state, seq_lens):
|
|
x = F.relu(self.fc1(input_dict["obs_flat"].float()))
|
|
h_in = hidden_state[0].reshape(-1, self.rnn_hidden_dim)
|
|
h = self.rnn(x, h_in)
|
|
q = self.fc2(h)
|
|
return q, [h]
|
|
|
|
|
|
def _get_size(obs_space):
|
|
return get_preprocessor(obs_space)(obs_space).size
|