Autonomous Planetary Landing via Deep Reinforcement Learning and Transfer Learning

Reinforcement Learning (RL) is a powerful tool that has been used to solve increasingly complex tasks. RL operates through repeated interactions of the learning agent with the environment, via trial and error. However, this learning process is extremely slow, requiring many interactions. In this thesis, we leverage previous knowledge so as to accelerate learning in multiagent RL problems. We propose knowledge reuse both from previous tasks and from other agents. Several flexible methods are introduced so that each of these two types of knowledge reuse is possible. This thesis adds important steps towards more flexible and broadly applicable multiagent transfer learning methods.

Download Full-text

Applying a Deep Q Network for OpenAIs Car Racing Game

10.14293/s2199-1006.1.sor-.ppd7fvs.v1 ◽

2020 ◽

Author(s):

Ali Fakhry

Keyword(s):

Machine Learning ◽

Reinforcement Learning ◽

Transfer Learning ◽

State Of The Art ◽

Learning Techniques ◽

Car Racing ◽

Custom Made ◽

Learning Technique ◽

Reward Threshold

The applications of Deep Q-Networks are seen throughout the field of reinforcement learning, a large subsect of machine learning. Using a classic environment from OpenAI, CarRacing-v0, a 2D car racing environment, alongside a custom based modification of the environment, a DQN, Deep Q-Network, was created to solve both the classic and custom environments. The environments are tested using custom made CNN architectures and applying transfer learning from Resnet18. While DQNs were state of the art years ago, using it for CarRacing-v0 appears somewhat unappealing and not as effective as other reinforcement learning techniques. Overall, while the model did train and the agent learned various parts of the environment, attempting to reach the reward threshold for the environment with this reinforcement learning technique seems problematic and difficult as other techniques would be more useful.

Download Full-text

Deep Reinforcement Learning for Transfer of Control Policies

Volume 2A: 45th Design Automation Conference ◽

10.1115/detc2019-97689 ◽

2019 ◽

Author(s):

James D. Cunningham ◽

Simon W. Miller ◽

Michael A. Yukish ◽

Timothy W. Simpson ◽

Conrad S. Tucker

Keyword(s):

Reinforcement Learning ◽

Transfer Learning ◽

Control Policy ◽

Dynamic State ◽

Test Case ◽

Original Design ◽

Control Policies ◽

Parallel Learning ◽

Rotor Design ◽

Control Knowledge

Abstract We present a form-aware reinforcement learning (RL) method to extend control knowledge from one design form to another, without losing the ability to control the original design. A major challenge in developing control knowledge is the creation of generalized control policies across designs of varying form. Our presented RL policy is form-aware because in addition to receiving dynamic state information about the environment, it also receives states that encode information about the form of the design that is being controlled. In this paper, we investigate the impact of this mixed state space on transfer learning. We present a transfer learning method for extending a control policy to a different design form, while continuing to expose the agent to the original design during the training of the new design. To demonstrate this concept, we present a case study of a multi-rotor aircraft simulation, wherein the designated task is to achieve a stable hover. We show that by introducing form states, an RL agent is able to learn a control policy to achieve the hovering task with both a four rotor and three rotor design at once, whereas without the form states it can only hover with the four rotor design. We also benchmark our method against a test case that removes the transfer learning component, as well as a test case that removes the continued exposure to the original design to show the value of each of these components. We find that form states, transfer learning, and parallel learning all contribute to a more robust control policy for the new design, and that parallel learning is especially important for maintaining control knowledge of the original design.

Download Full-text

An Introduction to Intertask Transfer for Reinforcement Learning

AI Magazine ◽

10.1609/aimag.v32i1.2329 ◽

2011 ◽

Vol 32 (1) ◽

pp. 15 ◽

Cited By ~ 18

Author(s):

Matthew E. Taylor ◽

Peter Stone

Keyword(s):

Reinforcement Learning ◽

Transfer Learning ◽

Learning Problem ◽

Open Problems ◽

Learning Framework ◽

Learning Domains ◽

Multiple Tasks ◽

Exciting Area ◽

Generalize Information ◽

Selection Of

Transfer learning has recently gained popularity due to the development of algorithms that can successfully generalize information across multiple tasks. This article focuses on transfer in the context of reinforcement learning domains, a general learning framework where an agent acts in an environment to maximize a reward signal. The goals of this article are to (1) familiarize readers with the transfer learning problem in reinforcement learning domains, (2) explain why the problem is both interesting and difﬁcult, (3) present a selection of existing techniques that demonstrate different solutions, and (4) provide representative open problems in the hope of encouraging additional research in this exciting area.

Download Full-text

Combined Reinforcement Learning via Abstract Representations

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33013582 ◽

2019 ◽

Vol 33 ◽

pp. 3582-3589 ◽

Cited By ~ 4

Author(s):

Vincent Francois-Lavet ◽

Yoshua Bengio ◽

Doina Precup ◽

Joelle Pineau

Keyword(s):

Reinforcement Learning ◽

State Space ◽

Transfer Learning ◽

Computationally Efficient ◽

Dimensional Representation ◽

Learning Methods ◽

Model Free ◽

Abstract Representations ◽

Low Dimensional ◽

New Strategies

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which opens up new strategies for interpretable AI, exploration and transfer learning.

Download Full-text