Learning to touch objects through stage-wise deep reinforcement learning

Learning complex behaviors through reinforcement learning is particularly challenging when reward is only available upon successful completion of the full behavior. In manipulation robotics, so-called shaping rewards are often used to overcome this problem. However, these usually require human engineering or (partial) world models describing, e.g., the kinematics of the robot or high-level modules for perception. Here we propose an alternative method to learn an object palm-touching task through a weakly-supervised and stage-wise learning of simpler tasks. First, the robot learns to fixate the object with its cameras. Second, the robot learns eye-hand coordination by learning to fixate its end effector. Third, using the previously acquired skills an informative shaping reward can be computed which facilitates efficient learning of the object palm-touching task. We demonstrate in simulation that learning the full task with this shaping reward is comparable to learning with an informative supervised reward.