Reinforcement Learning
A Composable Specification Language for Reinforcement Learning Tasks
However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward
Meta-Learning Representations for Continual Learning
Moreover, our algorithm is complementary to existing continual learning strategies, such as MER and GEM.
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Derek Yang, Li Zhao, Zichuan Lin, Tao Qin, Jiang Bian, Tie-Yan Liu
Neural Information Processing Systems http://nips.cc/
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
Chao Yang, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu, Junzhou Huang, Chuang Gan
Undoubtedly, conducting LfO is non-trivial .
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
Harm Van Seijen, Mehdi Fatemi, Arash Tavakoli
Neural Information Processing Systems http://nips.cc/
Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
This can uncover some of the "attended"
Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples
Tengyu Xu, Shaofeng Zou, Yingbin Liang
Neural Information Processing Systems http://nips.cc/
Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update
Su Young Lee, Choi Sungik, Sae-Young Chung
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation.
Reviewer # 1
DQN paper that we applied to all the baselines and our method for the experiment. Therefore, we are certain that we have provided a fair comparison. We apologize for the source of confusion about the update period in Appendix D. We meant "At each " We will correct this to prevent confusion. There have been many recent related works including the ones the Reviewer 1 cited. Unfortunately, we could not provide detailed differences/advances of them all in the limited amount of manuscript.