mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -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>
79 lines
2.8 KiB
Python
79 lines
2.8 KiB
Python
from ray.rllib.models.torch.torch_modelv2 import TorchModelV2
|
|
from ray.rllib.models.torch.misc import normc_initializer, valid_padding, \
|
|
SlimConv2d, SlimFC
|
|
from ray.rllib.models.tf.visionnet_v1 import _get_filter_config
|
|
from ray.rllib.utils.annotations import override
|
|
from ray.rllib.utils.framework import get_activation_fn
|
|
from ray.rllib.utils import try_import_torch
|
|
|
|
_, nn = try_import_torch()
|
|
|
|
|
|
class VisionNetwork(TorchModelV2, nn.Module):
|
|
"""Generic vision network."""
|
|
|
|
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)
|
|
|
|
activation = get_activation_fn(
|
|
model_config.get("conv_activation"), framework="torch")
|
|
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")
|
|
|
|
layers = []
|
|
(w, h, in_channels) = obs_space.shape
|
|
in_size = [w, h]
|
|
for out_channels, kernel, stride in filters[:-1]:
|
|
padding, out_size = valid_padding(in_size, kernel,
|
|
[stride, stride])
|
|
layers.append(
|
|
SlimConv2d(
|
|
in_channels,
|
|
out_channels,
|
|
kernel,
|
|
stride,
|
|
padding,
|
|
activation_fn=activation))
|
|
in_channels = out_channels
|
|
in_size = out_size
|
|
|
|
out_channels, kernel, stride = filters[-1]
|
|
layers.append(
|
|
SlimConv2d(
|
|
in_channels,
|
|
out_channels,
|
|
kernel,
|
|
stride,
|
|
None,
|
|
activation_fn=activation))
|
|
self._convs = nn.Sequential(*layers)
|
|
|
|
self._logits = SlimFC(
|
|
out_channels, num_outputs, initializer=nn.init.xavier_uniform_)
|
|
self._value_branch = SlimFC(
|
|
out_channels, 1, initializer=normc_initializer())
|
|
self._cur_value = None
|
|
|
|
@override(TorchModelV2)
|
|
def forward(self, input_dict, state, seq_lens):
|
|
features = self._hidden_layers(input_dict["obs"].float())
|
|
logits = self._logits(features)
|
|
self._cur_value = self._value_branch(features).squeeze(1)
|
|
return logits, state
|
|
|
|
@override(TorchModelV2)
|
|
def value_function(self):
|
|
assert self._cur_value is not None, "must call forward() first"
|
|
return self._cur_value
|
|
|
|
def _hidden_layers(self, obs):
|
|
res = self._convs(obs.permute(0, 3, 1, 2)) # switch to channel-major
|
|
res = res.squeeze(3)
|
|
res = res.squeeze(2)
|
|
return res
|