• Corpus ID: 195346739

DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

@article{Fridman2018DeepTrafficDF,
  title={DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning},
  author={Alex Fridman and Benedikt Jenik and Jack Terwilliger},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.02805}
}
We present a micro-traffic simulation (named "DeepTraffic") where the perception, control, and planning systems for one of the cars are all handled by a single neural network as part of a model-free, off-policy reinforcement learning process. The primary goal of DeepTraffic is to make the hands-on study of deep reinforcement learning accessible to thousands of students, educators, and researchers in order to inspire and fuel the exploration and evaluation of DQN variants and hyperparameter… 

Figures from this paper

Deep Surrogate Q-Learning for Autonomous Driving
TLDR
This work proposes Surrogate Q-learning, an efficient implementation based on a permutation equivariant deep neural network architecture of the Q-function to estimate action-values for a variable number of vehicles in sensor range and evaluates the method in the open traffic simulator SUMO and learns well performing driving policies on the real highD dataset.
Dynamic Input for Deep Reinforcement Learning in Autonomous Driving
TLDR
This paper employs the structure of Deep Sets in off-policy reinforcement learning for high-level decision making for reinforcement learning problems that have to deal with variable sized inputs, and shows that Deep Sets not only yield the best overall performance but also offer better generalization to unseen situations than the other approaches.
GridSim: A Vehicle Kinematics Engine for Deep Neuroevolutionary Control in Autonomous Driving
TLDR
GridSim is introduced, which is an autonomous driving simulator engine running a car-like robot architecture to generate occupancy grids from simulated sensors to study the performance of two deep learning approaches, deep reinforcement learning and driving behavioral learning through genetic algorithms.
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving
TLDR
This work proposes the novel Deep Scenes architecture, that can learn complex interaction-aware scene representations based on extensions of either 1) Deep Sets or 2) Graph Convolutional Networks.
Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous Traffic
TLDR
The model is composed of a data preprocessor that maps hybrid data into a data format called hyper-grid matrix, a two-stream deep neural network that extracts the hidden features, and a deep reinforcement learning network that learns the optimal policy.
Distributional Reinforcement Learning for Efficient Exploration
TLDR
This work proposes a novel and efficient exploration method for deep RL that has two components: a decaying schedule to suppress the intrinsic uncertainty and an exploration bonus calculated from the upper quantiles of the learned distribution.
Transfer Learning versus Multiagent Learning regarding Distributed Decision-Making in Highway Traffic
TLDR
This work explores the implications of distributed decision-making in mixed-intelligence traffic by means of a deep reinforcement learning approach, being deployed inside an elitist evolutionary algorithm for hyperparameter search.
Learning How to Avoiding Obstacles for End-to-End Driving with Conditional Imitation Learning
TLDR
A behavior-Cloning neural network architecture is proposed with the modified loss that enlarge the effects of errors for steer, which indicates the benefit to high an accuracy and the data augmentation of the image is crucial to the training of the proposed network.
CSCRS Road Safety Fellowship Report: A Human-Machine Collaborative Acceleration Controller Attained from Pixel Learning and Evolution Strategies
TLDR
A state-of-the-art reinforcement learning (RL) algorithm is adapted to train an auxiliary acceleration controller to help humans drive more efficiently than they would without augmentation by more than 50%.
An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural
...
...

References

SHOWING 1-10 OF 25 REFERENCES
Continuous control with deep reinforcement learning
TLDR
This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.
Asynchronous Methods for Deep Reinforcement Learning
TLDR
A conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers and shows that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.
Playing Atari with Deep Reinforcement Learning
TLDR
This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Deep Reinforcement Learning with Double Q-Learning
TLDR
This paper proposes a specific adaptation to the DQN algorithm and shows that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
TLDR
This paper applies deep reinforcement learning to the problem of forming long term driving strategies and shows how policy gradient iterations can be used without Markovian assumptions, and decomposes the problem into a composition of a Policy for Desires and trajectory planning with hard constraints.
Human-level control through deep reinforcement learning
TLDR
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Long-term Planning by Short-term Prediction
TLDR
This work considers planning problems, that often arise in autonomous driving applications, in which an agent should decide on immediate actions so as to optimize a long term objective, and proposes a full trajectory of the agent using a recurrent neural network, where unexplained factors are modeled as (additive) input nodes.
The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract)
TLDR
The promise of ALE is illustrated by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning, and an evaluation methodology made possible by ALE is proposed.
Reinforcement learning for robot soccer
TLDR
Several variants of the general batch learning framework are discussed, particularly tailored to the use of multilayer perceptrons to approximate value functions over continuous state spaces, which are successfully used to learn crucial skills in soccer-playing robots participating in the RoboCup competitions.
The Reinforcement Learning Competitions
TLDR
This article reports on the reinforcement learning competitions, which have been held annually since 2006, and describes the novel frameworks developed for the 2008 competition as well as the software infrastructure on which they rely.
...
...