Live Rewards Graph Option (#80)

* Adding an option to display a realtime plot of rewards using matplotlib

* Updating monitor back to where it was

* Adding a live_plot tool, also added an example (fee free to remove it)

examples/agents/random_agent_live_plot.py

@@ -0,0 +1,65 @@
+import logging
+import os, sys
+
+import gym
+from gym.monitoring.live_plot import LivePlot
+
+# The world's simplest agent!
+class RandomAgent(object):
+    def __init__(self, action_space):
+        self.action_space = action_space
+
+    def act(self, observation, reward, done):
+        return self.action_space.sample()
+
+if __name__ == '__main__':
+    # You can optionally set up the logger. Also fine to set the level
+    # to logging.DEBUG or logging.WARN if you want to change the
+    # amount of output.
+    logger = logging.getLogger()
+    logger.setLevel(logging.INFO)
+
+    env = gym.make('CartPole-v0' if len(sys.argv)<2 else sys.argv[1])
+
+    # You provide the directory to write to (can be an existing
+    # directory, including one with existing data -- all monitor files
+    # will be namespaced). You can also dump to a tempdir if you'd
+    # like: tempfile.mkdtemp().
+    outdir = '/tmp/random-agent-results'
+    env.monitor.start(outdir, force=True, seed=0)
+
+    # You may optionally include a LivePlot so that you can see
+    # how your agent is performing.  Use plotter.plot() to update 
+    # the graph. 
+    plotter = LivePlot(outdir)
+
+    # This declaration must go *after* the monitor call, since the
+    # monitor's seeding creates a new action_space instance with the
+    # appropriate pseudorandom number generator.
+    agent = RandomAgent(env.action_space)
+
+    episode_count = 100
+    max_steps = 200
+    reward = 0
+    done = False
+
+    for i in range(episode_count):
+        ob = env.reset()
+
+        for j in range(max_steps):
+            action = agent.act(ob, reward, done)
+            ob, reward, done, _ = env.step(action)
+            if done:
+                break
+                
+            plotter.plot()
+            env.render() 
+
+
+    # Dump result info to disk
+    env.monitor.close()
+
+    # Upload to the scoreboard. We could also do this from another
+    # process if we wanted.
+    logger.info("Successfully ran RandomAgent. Now trying to upload results to the scoreboard. If it breaks, you can always just try re-uploading the same results.")
+    gym.upload(outdir, algorithm_id='random')