luchaoqi · dependabot · Apr 14, 2020 · Apr 14, 2020 · Apr 14, 2020 · Apr 14, 2020
diff --git a/README.md b/README.md
diff --git a/super-mario-reinforcement-learning/logs/events.out.tfevents.1586850597.ubuntu b/super-mario-reinforcement-learning/logs/events.out.tfevents.1586850597.ubuntu
diff --git a/super-mario-reinforcement-learning/logs/events.out.tfevents.1586852454.ubuntu b/super-mario-reinforcement-learning/logs/events.out.tfevents.1586852454.ubuntu
diff --git a/super-mario-reinforcement-learning/logs/events.out.tfevents.1586852750.ubuntu b/super-mario-reinforcement-learning/logs/events.out.tfevents.1586852750.ubuntu
diff --git a/super-mario-reinforcement-learning/main.py b/super-mario-reinforcement-learning/main.py
@@ -1,13 +1,15 @@
 import time
 import numpy as np
 from nes_py.wrappers import JoypadSpace
-#BinarySpaceToDiscreteSpaceEnv
+#from nes_py.wrappers import BinarySpaceToDiscreteSpaceEnv
 import gym_super_mario_bros
 from gym_super_mario_bros.actions import RIGHT_ONLY
 from agent import DQNAgent
+# from gym import wrappers
 from wrappers import wrapper
 
 
+
 # Build env (first level, right only)
 env = gym_super_mario_bros.make('SuperMarioBros-1-1-v0')
 #env = BinarySpaceToDiscreteSpaceEnv(env, RIGHT_ONLY)

diff --git a/super-mario-reinforcement-learning/models/checkpoint b/super-mario-reinforcement-learning/models/checkpoint
@@ -0,0 +1,3 @@
+model_checkpoint_path: "model-1000000"
+all_model_checkpoint_paths: "model-500000"
+all_model_checkpoint_paths: "model-1000000"
diff --git a/super-mario-reinforcement-learning/models/model-1000000.data-00000-of-00001 b/super-mario-reinforcement-learning/models/model-1000000.data-00000-of-00001
diff --git a/super-mario-reinforcement-learning/models/model-1000000.index b/super-mario-reinforcement-learning/models/model-1000000.index
diff --git a/super-mario-reinforcement-learning/models/model-1000000.meta b/super-mario-reinforcement-learning/models/model-1000000.meta
diff --git a/super-mario-reinforcement-learning/models/model-500000.data-00000-of-00001 b/super-mario-reinforcement-learning/models/model-500000.data-00000-of-00001
diff --git a/super-mario-reinforcement-learning/models/model-500000.index b/super-mario-reinforcement-learning/models/model-500000.index
diff --git a/super-mario-reinforcement-learning/models/model-500000.meta b/super-mario-reinforcement-learning/models/model-500000.meta
diff --git a/super-mario-reinforcement-learning/replay.py b/super-mario-reinforcement-learning/replay.py
@@ -0,0 +1,21 @@
+from agent import DQNAgent
+from nes_py.wrappers import BinarySpaceToDiscreteSpaceEnv
+import gym_super_mario_bros
+from gym_super_mario_bros.actions import RIGHT_ONLY
+from wrappers import wrapper
+
+
+# Build env
+env = gym_super_mario_bros.make('SuperMarioBros-1-1-v0')
+env = BinarySpaceToDiscreteSpaceEnv(env, RIGHT_ONLY)
+env = wrapper(env)
+
+# Parameters
+states = (84, 84, 4)
+actions = env.action_space.n
+
+# Agent:q
+agent = DQNAgent(states=states, actions=actions, max_memory=100000, double_q=True)
+
+# Replay
+agent.replay(env=env, model_path='./models/final-vm-1', n_replay=1, plot=True)
diff --git a/super-mario-reinforcement-learning/requirements.txt b/super-mario-reinforcement-learning/requirements.txt
@@ -0,0 +1,116 @@
+absl-py==0.9.0
+apturl==0.5.2
+asn1crypto==0.24.0
+astor==0.8.1
+atari-py==0.2.6
+-e git+https://github.com/openai/baselines.git@ea25b9e8b234e6ee1bca43083f8f3cf974143998#egg=baselines
+bcrypt==3.1.6
+blinker==1.4
+Brlapi==0.6.7
+certifi==2018.8.24
+cffi==1.14.0
+chardet==3.0.4
+click==7.1.1
+cloudpickle==1.2.2
+command-not-found==0.3
+cryptography==2.6.1
+cupshelpers==1.0
+cycler==0.10.0
+Cython==0.29.16
+dbus-python==1.2.12
+defer==1.0.6
+dill==0.3.1.1
+distro==1.3.0
+distro-info===0.21ubuntu4
+duplicity==0.8.4
+entrypoints==0.3
+fasteners==0.12.0
+future==0.16.0
+gast==0.3.3
+glfw==1.11.0
+google-pasta==0.2.0
+grpcio==1.28.1
+gym==0.17.1
+gym-pull==0.1.7
+gym-super-mario-bros==7.3.0
+h5py==2.10.0
+httplib2==0.11.3
+idna==2.6
+imageio==2.8.0
+joblib==0.14.1
+Keras-Applications==1.0.8
+Keras-Preprocessing==1.1.0
+keyring==18.0.1
+keyrings.alt==3.1.1
+kiwisolver==1.2.0
+language-selector==0.1
+launchpadlib==1.10.7
+lazr.restfulclient==0.14.2
+lazr.uri==1.0.3
+lockfile==0.12.2
+louis==3.10.0
+macaroonbakery==1.2.3
+Mako==1.0.7
+Markdown==3.2.1
+MarkupSafe==1.1.0
+matplotlib==3.2.1
+monotonic==1.5
+mpi4py==3.0.3
+nes-py==8.1.1
+netifaces==0.10.4
+numpy==1.18.2
+oauthlib==2.1.0
+olefile==0.46
+opencv-python==4.2.0.34
+paramiko==2.6.0
+pexpect==4.6.0
+Pillow==6.1.0
+progressbar2==3.50.1
+protobuf==3.6.1
+pycairo==1.16.2
+pycparser==2.20
+pycrypto==2.6.1
+pycups==1.9.73
+pyglet==1.5.3
+PyGObject==3.34.0
+PyJWT==1.7.0
+pymacaroons==0.13.0
+PyNaCl==1.3.0
+pyparsing==2.4.7
+pyRFC3339==1.1
+python-apt==1.9.0+ubuntu1.3
+python-dateutil==2.7.3
+python-debian==0.1.36
+python-gflags==3.1.2
+python-utils==2.4.0
+pytz==2019.2
+pyxdg==0.25
+PyYAML==5.1.2
+pyzmq==19.0.0
+reportlab==3.5.23
+requests==2.21.0
+requests-unixsocket==0.1.5
+scipy==1.4.1
+SecretStorage==2.3.1
+simplejson==3.16.0
+six==1.12.0
+system-service==0.3
+systemd-python==234
+tensorboard==1.14.0
+tensorflow==1.14.0
+tensorflow-estimator==1.14.0
+termcolor==1.1.0
+tqdm==4.45.0
+ubuntu-advantage-tools==19.5
+ubuntu-drivers-common==0.0.0
+ufw==0.36
+unattended-upgrades==0.1
+urllib3==1.24.2
+usb-creator==0.3.7
+virtualenv==15.1.0
+wadllib==1.3.3
+Werkzeug==1.0.1
+wrappers==0.1.9
+wrapt==1.12.1
+xkit==0.0.0
+zmq==0.0.0
diff --git a/test.py b/test.py