Need To Be Done

Lectures

• CS294_HW

PAPER:

a. Deep Q-learning

• Playing Atari with Deep Reinforcement Learning, Mnih et al, 2013.

• Dueling Network Architectures for Deep Reinforcement Learning, Wang et al, 2015. Algorithm: Dueling DQN.

• Deep Reinforcement Learning with Double Q-learning, Hasselt et al 2015. Algorithm: Double DQN.

• Prioritized Experience Replay, Schaul et al, 2015. Algorithm: Prioritized Experience Replay (PER).

• Rainbow: Combining Improvements in Deep Reinforcement Learning, Hessel et al, 2017. Algorithm: Rainbow DQN.

b. Policy Gradients

• Asynchronous Methods for Deep Reinforcement Learning, Mnih et al, 2016. Algorithm: A3C.
• Trust Region Policy Optimization, Schulman et al, 2015. Algorithm: TRPO.
• High-Dimensional Continuous Control Using Generalized Advantage Estimation, Schulman et al, 2015. Algorithm: GAE.
• Proximal Policy Optimization Algorithms, Schulman et al, 2017. Algorithm: PPO-Clip, PPO-Penalty.
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, Haarnoja et al, 2018. Algorithm: SAC.

c. Deterministic Policy Gradients

• Continuous Control With Deep Reinforcement Learning, Lillicrap et al, 2015. Algorithm: DDPG.
• Addressing Function Approximation Error in Actor-Critic Methods, Fujimoto et al, 2018. Algorithm: TD3.

d. Meta-RL

• RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning, Duan et al, 2016. Algorithm: RL^2.
• Learning to Reinforcement Learn, Wang et al, 2016.
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, Finn et al, 2017. Algorithm: MAML.
• A Simple Neural Attentive Meta-Learner, Mishra et al, 2018. Algorithm: SNAIL.