PDF Publication Title:
Text from PDF Page: 038
3.8 experiments 30 Figure 2: 2D robot models used for locomotion experiments. From left to right: swimmer, hopper, walker. The hopper and walker present a particular challenge, due to underactuation and contact discontinuities. Input layer Fully connected layer 30 units Mean parameters dim u units Sampling Standard deviations Input layer Conv. layer 4×4 4×4 4×4 4×4 16 filters Conv. layer 4×4 4×4 4×4 4×4 16 filters Hidden layer 20 units Action probabilities Sampling Control Control Figure 3: Neural networks used for the locomotion task (left) and for playing Atari games (right). In the locomotion task, the sampled control (red diamond) is a vector u, whereas in Atari, it is a triple of integers that forms a factored representation of the action: see Section 3.13. quality locomotion controllers from scratch, which is considered to be a hard problem. We also show that these algorithms produce competitive results when learning policies for playing Atari games from images using convolutional neural networks with tens of thousands of parameters. 3.8.1 Simulated Robotic Locomotion We conducted the robotic locomotion experiments using the MuJoCo simulator [TET12]. The three simulated robots are shown in Figure 2. The states of the robots are their generalized positions and velocities, and the controls are joint torques. Underactuation, high dimensionality, and non-smooth dynamics due to contacts make these tasks very challenging. The following models are included in our evaluation: 1. Swimmer. 10-dimensional state space, linear reward for forward progress and a quadratic penalty on joint effort to produce the reward r(x, u) = vx − 10−5∥u∥2. The swimmer can propel itself forward by making an undulating motion. Joint angles and kinematics Screen inputPDF Image | OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS
PDF Search Title:
OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHSOriginal File Name Searched:
thesis-optimizing-deep-learning.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com (Standard Web Page)