Reinforcement Learning: Update README.md file & refactor some lines of our code

Author: DevOpsThinh

README.md

@@ -34,6 +34,10 @@ ___
 
 ### Illustrated results
 
+#### Custom environment with Gym
+- Coin Catcher<br>
+<img src="ml/rl_in_robotics/images/coin_catcher.gif" height="480"/> <br>
+
 #### Gym's Built-in & third-party environments
 - Lunar Lander<br>
 <img src="ml/rl_in_robotics/images/lunar_lander.gif" height="480"/> <br>

ml/rl_in_robotics/utility.py

@@ -26,7 +26,7 @@ def gym_rl_custom_tasks(env, episodes, action, mode, duration):
 def init_reset_environment(env):
     env = env
     init_state = env.reset()
-    return env
+    return init_state
 
 
 def gym_customize_tasks(env, episodes, action, mode="human", duration=1):
@@ -36,11 +36,14 @@ def gym_customize_tasks(env, episodes, action, mode="human", duration=1):
     for _ in range(episodes):
         if mode == "human":
             env.render(mode)
+        elif mode == "ascii":
+            env.render("ascii")
         else:
             env.render()
 
         action = action
-        state, reward, done, debug = env.step(action)
+        # state, reward, done, debug = env.step(action)
+        env.step(action)
         sleep(duration)