ALGORITHM.md

You can find more useful information at OpenAI Spinning Up

• RND / Random Network Distillation (30 Oct 2018)

  • Exploration by Random Network Distillation

• Dopamine (28 Sep 2018)

  • Dopamine: A Research Framework for Deep Reinforcement Learning

• Ape-X (2 May 2018)

  • Distributed Prioritized Experience Replay

• TD3 / Twin Delayed DDPG (26 Feb 2018)

  • Addressing Function Approximation Error in Actor-Critic Methods

• IMPALA / Importance Weighted Actor-Learner Architecture (5 Feb 2018)

  • IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

• N2D / NEC2DQN / Deep Q-learning using Neural Episodic Control (6 Jan 2018)

  • Faster Deep Q-learning using Neural Episodic Control

• SAC / Soft Actor Critic (4 Jan 2018)

  • Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

• Rainbow (6 Oct 2017)

  • Rainbow: Combining Improvements in Deep Reinforcement Learning

• A2C / Advantage Actor-Critic (18 Aug 2017)

  • A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C)

• ACKTR / Actor Critic using Kronecker-factored Trust Region (17 Aug 2017)

  • Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

• C51 / 51-atom agent (21 Jul 2017)

  • A Distributional Perspective on Reinforcement Learning

• PPO / Proximal Policy Optimization (20 Jul 2017)

  • Proximal Policy Optimization Algorithms

• HER / Hindsight Experience Replay (5 Jul 2017)

  • Hindsight Experience Replay

• ICM / Intrinsic Curiosity Module (15 May 2017 / 13 Aug 2018)

  • Curiosity-driven Exploration by Self-supervised Prediction
  • Large-Scale Study of Curiosity-Driven Learning

• DQFD / Deep Q-learning from Demonstration (12 Apr 2017)

  • Deep Q-learning from Demonstrations

• ACER / Actor-Critic with Experience Replay (3 Nov 2016)

  • Sample Efficient Actor-Critic with Experience Replay

• GAIL / Generative Adversarial Imitation (10 Jun 2016)

  • Generative Adversarial Imitation Learning

• CMA-ES / Covariance Matrix Adaptation Evolution Strategy (4 Apr 2016)

  • The CMA Evolution Strategy: A Tutorial

• A3C / Asynchronous Advantage Actor-Critic (4 Feb 2016)

  • Asynchronous Methods for Deep Reinforcement Learning

• NAF / Normalised Advantage Functions (2 Mar 2016)

  • Continuous Deep Q-Learning with Model-based Acceleration

• Dueling DQN (20 Nov 2015)

  • Dueling Network Architectures for Deep Reinforcement Learning

• PER / Prioritized Experience Replay (18 Nov 2015)

  • Prioritized Experience Replay

• DDQN / Double DQN (22 Sep 2015)

  • Deep Reinforcement Learning with Double Q-learning

• DDPG / Deep Deterministic Policy Gradient (9 Sep 2015)

  • Continuous control with deep reinforcement learning

• DRQN / Deep Recurrent Q-Network (23 Jul 2015)

  • Deep Recurrent Q-Learning for Partially Observable MDPs

• GAE / Generalized Advantage Estimation (8 Jun 2015)

  • High-Dimensional Continuous Control Using Generalized Advantage Estimation

• TRPO / Trust Region Policy Optimization (19 Feb 2015)

  • Trust Region Policy Optimization

• DPG / Deterministic Policy Gradient

  • Deterministic Policy Gradient Algorithms

• DQN / Deep Q Network (19 Dec 2013 / 25 Feb 2015)

  • Playing Atari with Deep Reinforcement Learning
  • Human-level control through deep reinforcement learning

• AC / Actor-Critic Algorithms (2000)

  • Actor-Critic Algorithms

• VPG / Vanilla Policy Gradient (29 Nov 1999)

  • Policy Gradient Methods for Reinforcement Learning with Function Approximation

• SARSA / State–action–reward–state–action (Sep 1994)

  • On-Line Q-Learning Using Connectionist Systems