Merge pull request #349 from prabhatnagarajan/prune_dqn_example

Move Atari Wrappers

Author: toslunar

examples/ale/atari_wrappers.py chainerrl/wrappers/atari_wrappers.pyexamples/ale/atari_wrappers.py renamed to chainerrl/wrappers/atari_wrappers.py

@@ -23,7 +23,7 @@
 from chainerrl import policy
 from chainerrl import v_function
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 def phi(x):

examples/ale/train_a2c_ale.py

@@ -28,7 +28,7 @@
 from chainerrl.recurrent import RecurrentChainMixin
 from chainerrl import v_function
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 class A3CFF(chainer.ChainList, a3c.A3CModel):

examples/ale/train_a3c_ale.py

@@ -28,7 +28,7 @@
 from chainerrl.optimizers import rmsprop_async
 from chainerrl.replay_buffer import EpisodicReplayBuffer
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 def main():

examples/ale/train_acer_ale.py

@@ -19,7 +19,7 @@
 from chainerrl import misc
 from chainerrl import replay_buffer
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 def main():

examples/ale/train_categorical_dqn_ale.py

@@ -26,7 +26,7 @@
 from chainerrl.q_functions import DuelingDQN
 from chainerrl import replay_buffer
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 class SingleSharedBias(chainer.Chain):

examples/ale/train_dqn_ale.py

@@ -25,7 +25,7 @@
 from chainerrl.q_functions import DuelingDQN
 from chainerrl import replay_buffer
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 class SingleSharedBias(chainer.Chain):

examples/ale/train_dqn_batch_ale.py

@@ -28,7 +28,7 @@
 from chainerrl import misc
 from chainerrl.optimizers import rmsprop_async
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 def main():

examples/ale/train_nsq_ale.py

@@ -22,7 +22,7 @@
 from chainerrl import policy
 from chainerrl import v_function
 
-import atari_wrappers
+from chainerrl.wrappers import atari_wrappers
 
 
 class A3CFF(chainer.ChainList, A3CModel):

examples/ale/train_ppo_ale.py

@@ -16,6 +16,8 @@ python train_dqn.py [options]
 - `--gpu`. Specifies the GPU. If you do not have a GPU on your machine, run the example with the option `--gpu -1`. E.g. `python train_dqn.py --gpu -1`.
 - `--env`. Specifies the environment. 
 - `--render`. Add this option to render the states in a GUI window.
+- `--seed`. This option specifies the random seed used.
+- `--outdir` This option specifies the output directory to which the results are written.
 
 To view the full list of options, either view the code or run the example with the `--help` option.