mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
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>
65 lines
2 KiB
Python
65 lines
2 KiB
Python
import numpy as np
|
|
from ray.rllib.utils import try_import_tf
|
|
|
|
tf = try_import_tf()
|
|
|
|
|
|
def normc_initializer(std=1.0):
|
|
def _initializer(shape, dtype=None, partition_info=None):
|
|
out = np.random.randn(*shape).astype(np.float32)
|
|
out *= std / np.sqrt(np.square(out).sum(axis=0, keepdims=True))
|
|
return tf.constant(out)
|
|
|
|
return _initializer
|
|
|
|
|
|
def conv2d(x,
|
|
num_filters,
|
|
name,
|
|
filter_size=(3, 3),
|
|
stride=(1, 1),
|
|
pad="SAME",
|
|
dtype=None,
|
|
collections=None):
|
|
if dtype is None:
|
|
dtype = tf.float32
|
|
|
|
with tf.variable_scope(name):
|
|
stride_shape = [1, stride[0], stride[1], 1]
|
|
filter_shape = [
|
|
filter_size[0], filter_size[1],
|
|
int(x.get_shape()[3]), num_filters
|
|
]
|
|
|
|
# There are "num input feature maps * filter height * filter width"
|
|
# inputs to each hidden unit.
|
|
fan_in = np.prod(filter_shape[:3])
|
|
# Each unit in the lower layer receives a gradient from: "num output
|
|
# feature maps * filter height * filter width" / pooling size.
|
|
fan_out = np.prod(filter_shape[:2]) * num_filters
|
|
# Initialize weights with random weights.
|
|
w_bound = np.sqrt(6 / (fan_in + fan_out))
|
|
|
|
w = tf.get_variable(
|
|
"W",
|
|
filter_shape,
|
|
dtype,
|
|
tf.random_uniform_initializer(-w_bound, w_bound),
|
|
collections=collections)
|
|
b = tf.get_variable(
|
|
"b", [1, 1, 1, num_filters],
|
|
initializer=tf.constant_initializer(0.0),
|
|
collections=collections)
|
|
return tf.nn.conv2d(x, w, stride_shape, pad) + b
|
|
|
|
|
|
def linear(x, size, name, initializer=None, bias_init=0):
|
|
w = tf.get_variable(
|
|
name + "/w", [x.get_shape()[1], size], initializer=initializer)
|
|
b = tf.get_variable(
|
|
name + "/b", [size], initializer=tf.constant_initializer(bias_init))
|
|
return tf.matmul(x, w) + b
|
|
|
|
|
|
def flatten(x):
|
|
return tf.reshape(x, [-1, np.prod(x.get_shape().as_list()[1:])])
|