Merge pull request #455 from muupan/fix-same-process-idx

Fix a bug of unintentionally using same process indices

Author: toslunar

examples/ale/train_a2c_ale.py

@@ -7,6 +7,7 @@
 standard_library.install_aliases()  # NOQA
 
 import argparse
+import functools
 import logging
 
 import chainer
@@ -123,7 +124,7 @@ def make_env(process_idx, test):
 
     def make_batch_env(test):
         return chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: make_env(idx, test))
+            [functools.partial(make_env, idx, test)
              for idx, env in enumerate(range(args.num_envs))])
 
     sample_env = make_env(0, test=False)

examples/ale/train_dqn_batch_ale.py

@@ -6,6 +6,7 @@
 from future import standard_library
 standard_library.install_aliases()  # NOQA
 import argparse
+import functools
 import os
 
 import chainer
@@ -161,7 +162,7 @@ def make_env(idx, test):
 
     def make_batch_env(test):
         vec_env = chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: make_env(idx, test))
+            [functools.partial(make_env, idx, test)
              for idx, env in enumerate(range(args.num_envs))])
         vec_env = chainerrl.wrappers.VectorFrameStack(vec_env, 4)
         return vec_env

examples/gym/train_a2c_gym.py

@@ -14,6 +14,7 @@
 from future import standard_library
 standard_library.install_aliases()  # NOQA
 import argparse
+import functools
 
 import chainer
 from chainer import functions as F
@@ -153,7 +154,7 @@ def make_env(process_idx, test):
 
     def make_batch_env(test):
         return chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: make_env(idx, test))
+            [functools.partial(make_env, idx, test)
              for idx, env in enumerate(range(args.num_envs))])
 
     sample_env = make_env(process_idx=0, test=False)

examples/gym/train_ddpg_batch_gym.py

@@ -5,6 +5,7 @@
 from future import standard_library
 standard_library.install_aliases()  # NOQA
 import argparse
+import functools
 import sys
 
 import chainer
@@ -106,7 +107,7 @@ def make_env(idx, test):
 
     def make_batch_env(test):
         return chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: make_env(idx, test))
+            [functools.partial(make_env, idx, test)
              for idx, env in enumerate(range(args.num_envs))])
 
     sample_env = make_env(0, test=False)

examples/gym/train_ppo_batch_gym.py

@@ -14,6 +14,7 @@
 from future import standard_library
 standard_library.install_aliases()  # NOQA
 import argparse
+import functools
 
 import chainer
 from chainer import functions as F
@@ -96,7 +97,7 @@ def make_env(process_idx, test):
 
     def make_batch_env(test):
         return chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: make_env(idx, test))
+            [functools.partial(make_env, idx, test)
              for idx, env in enumerate(range(args.num_envs))])
 
     # Only for getting timesteps, and obs-action spaces

tests/wrappers_tests/test_vector_frame_stack.py

@@ -6,6 +6,7 @@
 from future import standard_library
 standard_library.install_aliases()  # NOQA
 
+import functools
 import mock
 import unittest
 
@@ -68,14 +69,14 @@ def make_env(idx):
 
         # Wrap by FrameStack and MultiprocessVectorEnv
         fs_env = chainerrl.envs.MultiprocessVectorEnv(
-            [(lambda: FrameStack(
-                make_env(idx), k=self.k, channel_order='chw'))
+            [functools.partial(
+                FrameStack, make_env(idx), k=self.k, channel_order='chw')
              for idx, env in enumerate(range(self.num_envs))])
 
         # Wrap by MultiprocessVectorEnv and VectorFrameStack
         vfs_env = VectorFrameStack(
             chainerrl.envs.MultiprocessVectorEnv(
-                [(lambda: make_env(idx))
+                [functools.partial(make_env, idx)
                  for idx, env in enumerate(range(self.num_envs))]),
             k=self.k, stack_axis=0)