19 datasets found

A deep reinforcement learning model for playing Atari Pong.

The dataset used in this paper is a 2D docking problem benchmark, which is a spacecraft docking challenge. The goal is to train a DRL controller to safely navigate a deputy...

Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to...

The dataset used in the paper is a set of benchmarks for safe deep reinforcement learning. The benchmarks include Particle World and Mapless Navigation.

The proposed autonomous braking system learns an intelligent way of brake control from the experiences obtained under the simulated environment.

Multi-exit evacuation simulation dataset using Deep Reinforcement Learning (DRL) framework.

Four DRL agents were trained on the games MsPacman (simplified to Pac-Man), Space Invaders, Frostbite, and Breakout using the Deep Q-Network (DQN) implementation of the OpenAI...

The Rainbow algorithm was proposed by Hessel et al. (2018) and combines a number of recent advances, including double Q-learning, prioritized experience replay, dueling...

Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments

The dataset used in this paper is a human demonstration dataset for autonomous vehicles, consisting of images from a center camera.

The dataset used in this study for training and testing DRL agents to hedge American put options.

Autonomous robotic systems, like autonomous vehicles and robotic search and rescue, require efficient on-device training for continuous adaptation of Deep Reinforcement Learning...

The dataset is used for Deep Q-Networks (DQN) to optimize real-time traffic light control policies in emerging large-scale Intelligent Transportation Systems.

Grid path planning with deep reinforcement learning: Preliminary results.

A novel mobile robot navigation method based on deep reinforcement learning.

The dataset used in this paper for optimizing deep reinforcement learning for adaptive robotic arm control.

D4RL datasets for maze2d-umaze, maze2d-medium, maze2d-large, antmaze-umaze, antmaze-medium, antmaze-large, parking, soccer-sim, and soccer-physical tasks

Price movement prediction has always been one of the traders concerns in financial market trading. In order to increase their profit, they can analyze the historical data and...

A DRL library for automated stock trading with a focus on completeness, hands-on tutorials, and reproducibility.