Reinforcement Learning (RL)

4276 papers with code • 2 benchmarks • 18 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 implementations
28 papers
3,116
15 papers
45
14 papers
1,176
See all 33 libraries.

Most implemented papers

Continuous control with deep reinforcement learning

ray-project/ray 9 Sep 2015

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain.

Playing Atari with Deep Reinforcement Learning

labmlai/annotated_deep_learning_paper_implementations 19 Dec 2013

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.

Deep Reinforcement Learning with Double Q-learning

labmlai/annotated_deep_learning_paper_implementations 22 Sep 2015

The popular Q-learning algorithm is known to overestimate action values under certain conditions.

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

cbfinn/maml ICML 2017

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.

Prioritized Experience Replay

labmlai/annotated_deep_learning_paper_implementations 18 Nov 2015

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.

Dueling Network Architectures for Deep Reinforcement Learning

labmlai/annotated_deep_learning_paper_implementations 20 Nov 2015

In recent years there have been many successes of using deep representations in reinforcement learning.

Asynchronous Methods for Deep Reinforcement Learning

ray-project/ray 4 Feb 2016

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.

Addressing Function Approximation Error in Actor-Critic Methods

sfujim/TD3 ICML 2018

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies.