Reinforcement Learning (RL)
3912 papers with code • 1 benchmarks • 15 datasets
Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.
Libraries
Use these libraries to find Reinforcement Learning (RL) models and implementationsSubtasks
Most implemented papers
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
The game of chess is the most widely-studied domain in the history of artificial intelligence.
DARTS: Differentiable Architecture Search
This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner.
Soft Actor-Critic Algorithms and Applications
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
OpenAI Gym
OpenAI Gym is a toolkit for reinforcement learning research.
Weight Uncertainty in Neural Networks
We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop.
Rainbow: Combining Improvements in Deep Reinforcement Learning
The deep reinforcement learning community has made several independent improvements to the DQN algorithm.
Self-critical Sequence Training for Image Captioning
In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized.
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
The purpose of this technical report is two-fold.
A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem
They are, along with a number of recently reviewed or published portfolio-selection strategies, examined in three back-test experiments with a trading period of 30 minutes in a cryptocurrency market.
Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL).