mirror of
https://github.com/vale981/ray
synced 2025-03-09 21:06:39 -04:00
428516056a
* Policy-classes cleanup and torch/tf unification. - Make Policy abstract. - Add `action_dist` to call to `extra_action_out_fn` (necessary for PPO torch). - Move some methods and vars to base Policy (from TFPolicy): num_state_tensors, ACTION_PROB, ACTION_LOGP and some more. * Fix `clip_action` import from Policy (should probably be moved into utils altogether). * - Move `is_recurrent()` and `num_state_tensors()` into TFPolicy (from DynamicTFPolicy). - Add config to all Policy c'tor calls (as 3rd arg after obs and action spaces). * Add `config` to c'tor call to TFPolicy. * Add missing `config` to c'tor call to TFPolicy in marvil_policy.py. * Fix test_rollout_worker.py::MockPolicy and BadPolicy classes (Policy base class is now abstract). * Fix LINT errors in Policy classes. * Implement StatefulPolicy abstract methods in test cases: test_multi_agent_env.py. * policy.py LINT errors. * Create a simple TestPolicy to sub-class from when testing Policies (reduces code in some test cases). * policy.py - Remove abstractmethod from `apply_gradients` and `compute_gradients` (these are not required iff `learn_on_batch` implemented). - Fix docstring of `num_state_tensors`. * Make QMIX torch Policy a child of TorchPolicy (instead of Policy). * QMixPolicy add empty implementations of abstract Policy methods. * Store Policy's config in self.config in base Policy c'tor. * - Make only compute_actions in base Policy's an abstractmethod and provide pass implementation to all other methods if not defined. - Fix state_batches=None (most Policies don't have internal states). * Cartpole tf learning. * Cartpole tf AND torch learning (in ~ same ts). * Cartpole tf AND torch learning (in ~ same ts). 2 * Cartpole tf (torch syntax-broken) learning (in ~ same ts). 3 * Cartpole tf AND torch learning (in ~ same ts). 4 * Cartpole tf AND torch learning (in ~ same ts). 5 * Cartpole tf AND torch learning (in ~ same ts). 6 * Cartpole tf AND torch learning (in ~ same ts). Pendulum tf learning. * WIP. * WIP. * SAC torch learning Pendulum. * WIP. * SAC torch and tf learning Pendulum and Cartpole after cleanup. * WIP. * LINT. * LINT. * SAC: Move policy.target_model to policy.device as well. * Fixes and cleanup. * Fix data-format of tf keras Conv2d layers (broken for some tf-versions which have data_format="channels_first" as default). * Fixes and LINT. * Fixes and LINT. * Fix and LINT. * WIP. * Test fixes and LINT. * Fixes and LINT. Co-authored-by: Sven Mika <sven@Svens-MacBook-Pro.local>
118 lines
4.7 KiB
Python
118 lines
4.7 KiB
Python
from ray.rllib.models.tf.tf_modelv2 import TFModelV2
|
|
from ray.rllib.models.tf.visionnet_v1 import _get_filter_config
|
|
from ray.rllib.models.tf.misc import normc_initializer
|
|
from ray.rllib.utils.framework import get_activation_fn, try_import_tf
|
|
|
|
tf = try_import_tf()
|
|
|
|
|
|
class VisionNetwork(TFModelV2):
|
|
"""Generic vision network implemented in ModelV2 API."""
|
|
|
|
def __init__(self, obs_space, action_space, num_outputs, model_config,
|
|
name):
|
|
super(VisionNetwork, self).__init__(obs_space, action_space,
|
|
num_outputs, model_config, name)
|
|
|
|
activation = get_activation_fn(model_config.get("conv_activation"))
|
|
filters = model_config.get("conv_filters")
|
|
if not filters:
|
|
filters = _get_filter_config(obs_space.shape)
|
|
no_final_linear = model_config.get("no_final_linear")
|
|
vf_share_layers = model_config.get("vf_share_layers")
|
|
|
|
inputs = tf.keras.layers.Input(
|
|
shape=obs_space.shape, name="observations")
|
|
last_layer = inputs
|
|
|
|
# Build the action layers
|
|
for i, (out_size, kernel, stride) in enumerate(filters[:-1], 1):
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
out_size,
|
|
kernel,
|
|
strides=(stride, stride),
|
|
activation=activation,
|
|
padding="same",
|
|
data_format="channels_last",
|
|
name="conv{}".format(i))(last_layer)
|
|
out_size, kernel, stride = filters[-1]
|
|
|
|
# No final linear: Last layer is a Conv2D and uses num_outputs.
|
|
if no_final_linear:
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
num_outputs,
|
|
kernel,
|
|
strides=(stride, stride),
|
|
activation=activation,
|
|
padding="valid",
|
|
data_format="channels_last",
|
|
name="conv_out")(last_layer)
|
|
conv_out = last_layer
|
|
# Finish network normally (w/o overriding last layer size with
|
|
# `num_outputs`), then add another linear one of size `num_outputs`.
|
|
else:
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
out_size,
|
|
kernel,
|
|
strides=(stride, stride),
|
|
activation=activation,
|
|
padding="valid",
|
|
data_format="channels_last",
|
|
name="conv{}".format(i + 1))(last_layer)
|
|
conv_out = tf.keras.layers.Conv2D(
|
|
num_outputs, [1, 1],
|
|
activation=None,
|
|
padding="same",
|
|
data_format="channels_last",
|
|
name="conv_out")(last_layer)
|
|
|
|
# Build the value layers
|
|
if vf_share_layers:
|
|
last_layer = tf.keras.layers.Lambda(
|
|
lambda x: tf.squeeze(x, axis=[1, 2]))(last_layer)
|
|
value_out = tf.keras.layers.Dense(
|
|
1,
|
|
name="value_out",
|
|
activation=None,
|
|
kernel_initializer=normc_initializer(0.01))(last_layer)
|
|
else:
|
|
# build a parallel set of hidden layers for the value net
|
|
last_layer = inputs
|
|
for i, (out_size, kernel, stride) in enumerate(filters[:-1], 1):
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
out_size,
|
|
kernel,
|
|
strides=(stride, stride),
|
|
activation=activation,
|
|
padding="same",
|
|
data_format="channels_last",
|
|
name="conv_value_{}".format(i))(last_layer)
|
|
out_size, kernel, stride = filters[-1]
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
out_size,
|
|
kernel,
|
|
strides=(stride, stride),
|
|
activation=activation,
|
|
padding="valid",
|
|
data_format="channels_last",
|
|
name="conv_value_{}".format(i + 1))(last_layer)
|
|
last_layer = tf.keras.layers.Conv2D(
|
|
1, [1, 1],
|
|
activation=None,
|
|
padding="same",
|
|
data_format="channels_last",
|
|
name="conv_value_out")(last_layer)
|
|
value_out = tf.keras.layers.Lambda(
|
|
lambda x: tf.squeeze(x, axis=[1, 2]))(last_layer)
|
|
|
|
self.base_model = tf.keras.Model(inputs, [conv_out, value_out])
|
|
self.register_variables(self.base_model.variables)
|
|
|
|
def forward(self, input_dict, state, seq_lens):
|
|
# explicit cast to float32 needed in eager
|
|
model_out, self._value_out = self.base_model(
|
|
tf.cast(input_dict["obs"], tf.float32))
|
|
return tf.squeeze(model_out, axis=[1, 2]), state
|
|
|
|
def value_function(self):
|
|
return tf.reshape(self._value_out, [-1])
|