Learning What to Attend to: Using bisimulation metrics to explore and improve upon what a deep reinforcement learning agent learns

We analyze the internal representations that deep Reinforcement Learning (RL) agents form of their environments and whether these representations correspond to what such agents should ideally learn. The purpose of this comparison is both a better understanding of why certain algorithms or network architectures perform better than others and the...

Comparing Exploration Approaches in Deep Reinforcement Learning for Traffic Light Control

Identifying the most efficient exploration approach for deep reinforcement learning in traffic light control is not a trivial task, and can be a critical step in the development of reinforcement learning solutions that can effectively reduce traffic congestion. It is common to use baseline dithering methods such as $\epsilon$-greedy. However,...

Exploration and Coverage: A Deep Reinforcement Learning Approach

This work addresses the problem of exploration and coverage using visual inputs. Exploration and coverage is a fundamental problem in mobile robotics, the goal of which is to explore an unknown environment in order to gain vital information. Some of the diverse scenarios and applications in which exploratory robots can have a significant impact...

Multi Agent Deep Recurrent Q-Learning for Different Traffic Demands

In today’s scenario due to rapid urbanisation there has been a shift of population from rural to urban areas especially in developing countries in search of better opportunities. This has lead to unprecedented growth of cities leading to various urbanisation problems. One of the main problems that comes across in urban areas is the increased...

Sample effficient deep reinforcement learning for control

The arrival of intelligent, general-purpose robots that can learn to perform new tasks autonomously has been promised for a long time now. Deep reinforcement learning, which combines reinforcement learning with deep neural network function approximation, has the potential to enable robots to learn to perform a wide range of new tasks while...

Learning What to Attend to: Using Bisimulation Metrics to Explore and Improve Upon What a Deep Reinforcement Learning Agent Learns

Recent years have seen a surge of algorithms and architectures for deep Re-<br/>inforcement Learning (RL), many of which have shown remarkable success for<br/>various problems. Yet, little work has attempted to relate the performance of<br/>these algorithms and architectures to what the resulting deep RL agents actu-<br/>ally learn, and whether...

A method of personalized driving decision for smart car based on deep reinforcement learning

To date, automatic driving technology has become a hotspot in academia. It is necessary to provide a personalization of automatic driving decision for each passenger. The purpose of this paper is to propose a self-learning method for personalized driving decisions. First, collect and analyze driving data from different drivers to set learning...

Deep reinforcement learning for acceptance strategy in bilateral negotiations

This paper introduces an acceptance strategy based on reinforcement learning for automated bilateral negotiation, where negotiating agents bargain on multiple issues in a variety of negotiation scenarios. Several acceptance strategies based on predefined rules have been introduced in the automated negotiation literature. Those rules mostly...

NL to PDDL: One-Shot Learning of Planning Domains from Natural Language Process Manuals

Automated Planning (AP) is a key component of Artificial General Intelligence and has been successfully employed in applications ranging from scheduling observations of Hubble Space Telescope to generating dialogue agents. A significant bottleneck for its widespread adoption is acquiring accurate domain models which formally encode the planning...

Multi-Agent Deep Reinforcement Learning for Automated Highway Driving

Recent advances in Deep Reinforcement Learning have sparked new interest in many different research topics, including Automated Highway Driving where agents model autonomous vehicles. The main advantage of Deep Reinforcement Learning is that the training algorithm is adaptable to its environment. In highway driving, researchers often simplify...

Prioritized Experience Replay based on the Wasserstein Metric in Deep Reinforcement Learning: The regularizing effect of modelling return distributions

This thesis tests the hypothesis that distributional deep reinforcement learning (RL) algorithms get an increased performance over expectation based deep RL because of the regularizing effect of fitting a more complex model. This hypothesis was tested by comparing two variations of the distributional QR-DQN algorithm combined with prioritized...

Vision-based navigation using deep reinforcement learning

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To...

Flexible Curriculum Learning for Deep Reinforcement Learning Agents

Reinforcement Learning (RL) is a learning paradigm that learns by interacting with the environment. In practice, a RL agent needs to perform many actions to sample rewards and state transitions from their environments. Recent advances in using deep neural networks as function approximators reduce the sample complexity in very high dimensional...

Limit order placement optimization with Deep Reinforcement Learning: Learning from patterns in cryptocurrency market data

For various reasons, financial institutions often make use of high-level trading strategies when buying and selling assets. Many individuals, irrespective or their level of prior trading knowledge, have recently entered the field of trading due to the increasing popularity of cryptocurrencies, which offer a low entry barrier for trading....

Deep Reinforcement Learning for Goal-directed Visual Navigation

Safe navigation in a cluttered environment is a key capability for the autonomous operation of Micro Aerial Vehicles (MAVs). This work explores a (deep) Reinforcement Learning (RL) based approach for monocular vision based obstacle avoidance and goal directed navigation for MAVs in cluttered environments. We investigated this problem in the...