mirror of
https://github.com/vale981/ray
synced 2025-03-07 02:51:39 -05:00
2b3d0c691f
Co-authored-by: Richard Liaw <rliaw@berkeley.edu> Co-authored-by: Sven Mika <sven@anyscale.io> Co-authored-by: sven1977 <svenmika1977@gmail.com>
117 lines
4.2 KiB
Python
117 lines
4.2 KiB
Python
from gym.spaces import Dict
|
|
|
|
from ray.rllib.models.tf.fcnet import FullyConnectedNetwork
|
|
from ray.rllib.models.tf.tf_modelv2 import TFModelV2
|
|
from ray.rllib.models.torch.torch_modelv2 import TorchModelV2
|
|
from ray.rllib.models.torch.fcnet import FullyConnectedNetwork as TorchFC
|
|
from ray.rllib.utils.framework import try_import_tf, try_import_torch
|
|
from ray.rllib.utils.torch_utils import FLOAT_MIN
|
|
|
|
tf1, tf, tfv = try_import_tf()
|
|
torch, nn = try_import_torch()
|
|
|
|
|
|
class ActionMaskModel(TFModelV2):
|
|
"""Model that handles simple discrete action masking.
|
|
|
|
This assumes the outputs are logits for a single Categorical action dist.
|
|
Getting this to work with a more complex output (e.g., if the action space
|
|
is a tuple of several distributions) is also possible but left as an
|
|
exercise to the reader.
|
|
"""
|
|
|
|
def __init__(self, obs_space, action_space, num_outputs, model_config,
|
|
name, **kwargs):
|
|
|
|
orig_space = getattr(obs_space, "original_space", obs_space)
|
|
assert isinstance(orig_space, Dict) and \
|
|
"action_mask" in orig_space.spaces and \
|
|
"observations" in orig_space.spaces
|
|
|
|
super().__init__(obs_space, action_space, num_outputs, model_config,
|
|
name)
|
|
|
|
self.internal_model = FullyConnectedNetwork(
|
|
orig_space["observations"], action_space, num_outputs,
|
|
model_config, name + "_internal")
|
|
|
|
# disable action masking --> will likely lead to invalid actions
|
|
self.no_masking = model_config["custom_model_config"].get(
|
|
"no_masking", False)
|
|
|
|
def forward(self, input_dict, state, seq_lens):
|
|
# Extract the available actions tensor from the observation.
|
|
action_mask = input_dict["obs"]["action_mask"]
|
|
|
|
# Compute the unmasked logits.
|
|
logits, _ = self.internal_model({
|
|
"obs": input_dict["obs"]["observations"]
|
|
})
|
|
|
|
# If action masking is disabled, directly return unmasked logits
|
|
if self.no_masking:
|
|
return logits, state
|
|
|
|
# Convert action_mask into a [0.0 || -inf]-type mask.
|
|
inf_mask = tf.maximum(tf.math.log(action_mask), tf.float32.min)
|
|
masked_logits = logits + inf_mask
|
|
|
|
# Return masked logits.
|
|
return masked_logits, state
|
|
|
|
def value_function(self):
|
|
return self.internal_model.value_function()
|
|
|
|
|
|
class TorchActionMaskModel(TorchModelV2, nn.Module):
|
|
"""PyTorch version of above ActionMaskingModel."""
|
|
|
|
def __init__(
|
|
self,
|
|
obs_space,
|
|
action_space,
|
|
num_outputs,
|
|
model_config,
|
|
name,
|
|
**kwargs,
|
|
):
|
|
orig_space = getattr(obs_space, "original_space", obs_space)
|
|
assert isinstance(orig_space, Dict) and \
|
|
"action_mask" in orig_space.spaces and \
|
|
"observations" in orig_space.spaces
|
|
|
|
TorchModelV2.__init__(self, obs_space, action_space, num_outputs,
|
|
model_config, name, **kwargs)
|
|
nn.Module.__init__(self)
|
|
|
|
self.internal_model = TorchFC(orig_space["observations"], action_space,
|
|
num_outputs, model_config,
|
|
name + "_internal")
|
|
|
|
# disable action masking --> will likely lead to invalid actions
|
|
self.no_masking = False
|
|
if "no_masking" in model_config["custom_model_config"]:
|
|
self.no_masking = model_config["custom_model_config"]["no_masking"]
|
|
|
|
def forward(self, input_dict, state, seq_lens):
|
|
# Extract the available actions tensor from the observation.
|
|
action_mask = input_dict["obs"]["action_mask"]
|
|
|
|
# Compute the unmasked logits.
|
|
logits, _ = self.internal_model({
|
|
"obs": input_dict["obs"]["observations"]
|
|
})
|
|
|
|
# If action masking is disabled, directly return unmasked logits
|
|
if self.no_masking:
|
|
return logits, state
|
|
|
|
# Convert action_mask into a [0.0 || -inf]-type mask.
|
|
inf_mask = torch.clamp(torch.log(action_mask), min=FLOAT_MIN)
|
|
masked_logits = logits + inf_mask
|
|
|
|
# Return masked logits.
|
|
return masked_logits, state
|
|
|
|
def value_function(self):
|
|
return self.internal_model.value_function()
|