Reinforcement Learning
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.
Multi-Step Generalized Policy Improvement by Leveraging Approximate Models Lucas N. Alegre 1, 2 Ana L. C. Bazzan 1 Ann Now รฉ 2 Bruno C. da Silva 3 1
We introduce a principled method for performing zero-shot transfer in reinforcement learning (RL) by exploiting approximate models of the environment. Zero-shot transfer in RL has been investigated by leveraging methods rooted in generalized policy improvement (GPI) and successor features (SFs).
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
Nan Rosemary Ke, Anirudh Goyal ALIAS PARTH GOYAL, Olexa Bilaniuk, Jonathan Binas, Michael C. Mozer, Chris Pal, Yoshua Bengio
The T = 100, itisclearthatT grows.SABstill tocompleteT = 5000, whereasT = 2000bothv self-attention 1/8 = 12.5%).
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
Chao Yang, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu, Junzhou Huang, Chuang Gan
Incontrast toLearning fromDemonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g.
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
Harm Van Seijen, Mehdi Fatemi, Arash Tavakoli
Weproveconvergence for this method under standard assumptions and demonstrate empirically that it indeed enables lowerdiscount factors forapproximate reinforcement-learning methods.
Learning to Navigate in Cities Without a Map
Piotr Mirowski, Matt Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, koray kavukcuoglu, Andrew Zisserman, Raia Hadsell
Neural Information Processing Systems http://nips.cc/
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional objectoriented framework that has provably efficient learning bounds with respect to samplecomplexity.
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/
