这是indexloc提供的服务，不要输入任何密码
Skip to content

Add map_action_inverse for fixing error of storing random action #568

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 12, 2022
Merged

Add map_action_inverse for fixing error of storing random action #568

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9442f57
Inverse map action
Jimenius Mar 12, 2022
d7db6fa
Merge branch 'master' into inverse_map_action
Trinkle23897 Mar 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions tianshou/data/collector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,7 @@ def collect(
]
except TypeError: # envpool's action space is not for per-env
act_sample = [self._action_space.sample() for _ in ready_env_ids]
act_sample = self.policy.map_action_inverse(act_sample) # type: ignore
self.data.update(act=act_sample)
else:
if no_grad:
Expand Down Expand Up @@ -451,6 +452,7 @@ def collect(
]
except TypeError: # envpool's action space is not for per-env
act_sample = [self._action_space.sample() for _ in ready_env_ids]
act_sample = self.policy.map_action_inverse(act_sample) # type: ignore
self.data.update(act=act_sample)
else:
if no_grad:
Expand Down
29 changes: 28 additions & 1 deletion tianshou/policy/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
from abc import ABC, abstractmethod
from typing import Any, Callable, Dict, Optional, Tuple, Union
from typing import Any, Callable, Dict, List, Optional, Tuple, Union

import gym
import numpy as np
Expand Down Expand Up @@ -178,6 +178,33 @@ def map_action(self, act: Union[Batch, np.ndarray]) -> Union[Batch, np.ndarray]:
act = low + (high - low) * (act + 1.0) / 2.0 # type: ignore
return act

def map_action_inverse(
self, act: Union[Batch, List, np.ndarray]
) -> Union[Batch, List, np.ndarray]:
"""Inverse operation to :meth:`~tianshou.policy.BasePolicy.map_action`.

This function is called in :meth:`~tianshou.data.Collector.collect` for
random initial steps. It scales [action_space.low, action_space.high] to
the value ranges of policy.forward.

:param act: a data batch, list or numpy.ndarray which is the action taken
by gym.spaces.Box.sample().

:return: action remapped.
"""
if isinstance(self.action_space, gym.spaces.Box):
act = to_numpy(act)
if isinstance(act, np.ndarray):
if self.action_scaling:
low, high = self.action_space.low, self.action_space.high
scale = high - low
eps = np.finfo(np.float32).eps.item()
scale[scale < eps] += eps
act = (act - low) * 2.0 / scale - 1.0
if self.action_bound_method == "tanh":
act = (np.log(1.0 + act) - np.log(1.0 - act)) / 2.0 # type: ignore
return act

def process_fn(
self, batch: Batch, buffer: ReplayBuffer, indices: np.ndarray
) -> Batch:
Expand Down