Merge branch 'master' of https://github.com/ShangtongZhang/DeepRL

deep_rl/utils/config.py

@@ -60,6 +60,7 @@ class Config:
         self.test_interval = 0
         self.test_repetitions = 10
         self.evaluation_env = None
+        self.termination_regularizer = 0
 
     def add_argument(self, *args, **kwargs):
         self.parser.add_argument(*args, **kwargs)

deep_rl/utils/plot.py

@@ -1,7 +1,7 @@
 # Adapted from  https://github.com/openai/baselines/blob/master/baselines/results_plotter.py
 
+from ..component.bench import load_monitor_log
 import numpy as np
-from ..component import *
 import os
 import re
 
@@ -44,7 +44,7 @@ class Plotter:
     def load_results(self, dirs, max_timesteps=1e8, x_axis=X_TIMESTEPS, episode_window=100):
         tslist = []
         for dir in dirs:
-            ts = component.load_monitor_log(dir)
+            ts = load_monitor_log(dir)
             ts = ts[ts.l.cumsum() <= max_timesteps]
             tslist.append(ts)
         xy_list = [self.ts2xy(ts, x_axis) for ts in tslist]