[1999] [Options] Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning[1999] [Policy Gradient] Policy Gradient Methods for Reinforcement Learning with Function Approximation[1999] [Actor-Critic] Actor-Critic Algorithms[2012] [OffPAC] Off-Policy Actor-Critic[2014] [DPG] Deterministic Policy Gradient Algorithms[2015] [GAE] High-Dimensional Continuous Control Using Generalized Advantage Estimation[2015] [DQN] Human-level control through deep reinforcement learning[2015] [Gorila DQN] Massively Parallel Methods for Deep Reinforcement Learning[2015] [Double DQN] Deep Reinforcement Learning with Double Q-learning[2015] [DDPG] Continuous control with deep reinforcement learning[2015] [TRPO] Trust Region Policy Optimization[2016] [A3C] Asynchronous Methods for Deep Reinforcement Learning[2016] [AlphaGo] Mastering the Game of Go with Deep Neural Networks and Tree Search[2017] [MADDPG] Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments[2017] [Option-Critic] The Option-Critic Architecture[2017] [PPO] Proximal Policy Optimization Algorithms[2017] [AlphaGo Zero] Mastering the game of Go without human knowledge[2017] [CPO] Constrained Policy Optimization[2017] [Shielding] Safe Reinforcement Learning via Shielding[2018] [SAC] Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor[2018] [TD3] Addressing Function Approximation Error in Actor-Critic Methods[2018] [QT-Opt] QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation[2018] [BCQ] Off-Policy Deep Reinforcement Learning without Exploration[2020] [Offline RL] Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems[2021] [RMA] RMA: Rapid Motor Adaptation for Legged Robots[2022] [InstructGPT] Training language models to follow instructions with human feedback[2023] [SWIM] Structured World Models from Human Videos[2023] [Safe RLHF] Safe RLHF: Safe Reinforcement Learning from Human Feedback[2024] [GRPO] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models[2025] [self-improving-efms] Self-Improving Embodied Foundation Models[2025] [RECAP]π 0.6 ∗ π^∗_{0.6}π0.6∗​: a VLA That Learns From Experience[2026] [LATENT] Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data