Add overall setting and ddpg baseline (#1)

* Add overall CI settings

* Add specific build dir to travis

* Add before install/script condition to travis

* Add ddpg baseline

* Add wandb, remove algorithms except ddpg

* Remove init file in script

* Separate config file for ddpg

* Remove unnecessary examples

* Remove unnecessary args opt

* Add pre-commit setting

* Change pre-commit settings

* Change travis-ci setting

* Fix travis-ci issue

* Modify argparse arguments, fix requirements

* Change arguments order

scripts/algorithms/common/noise.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+"""Noise classes for baselines."""
+
+import copy
+import random
+
+import numpy as np
+
+
+class OUNoise:
+    """Ornstein-Uhlenbeck process.
+
+    Taken from Udacity deep-reinforcement-learning github repository:
+    https://github.com/udacity/deep-reinforcement-learning/blob/master/
+    ddpg-pendulum/ddpg_agent.py
+    """
+
+    def __init__(self, size, seed, mu=0.0, theta=0.15, sigma=0.2):
+        """Initialize parameters and noise process."""
+        self.state = np.float64(0.0)
+        self.mu = mu * np.ones(size)
+        self.theta = theta
+        self.sigma = sigma
+        self.reset()
+
+        random.seed(seed)
+
+    def reset(self):
+        """Reset the internal state (= noise) to mean (mu)."""
+        self.state = copy.copy(self.mu)
+
+    def sample(self):
+        """Update internal state and return it as a noise sample."""
+        x = self.state
+        dx = self.theta * (self.mu - x) + self.sigma * np.array(
+            [random.random() for _ in range(len(x))]
+        )
+        self.state = x + dx
+        return self.state