【DL輪読会】Efficiently Modeling Long Sequences with Structured State SpacesDeep Learning JP
This document summarizes a research paper on modeling long-range dependencies in sequence data using structured state space models and deep learning. The proposed S4 model (1) derives recurrent and convolutional representations of state space models, (2) improves long-term memory using HiPPO matrices, and (3) efficiently computes state space model convolution kernels. Experiments show S4 outperforms existing methods on various long-range dependency tasks, achieves fast and memory-efficient computation comparable to efficient Transformers, and performs competitively as a general sequence model.
NIPS KANSAI Reading Group #7: 逆強化学習の行動解析への応用Eiji Uchibe
Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning, Ecosphere,
Modeling sensory-motor decisions in natural behavior, PLoS Comp. Biol.
【DL輪読会】Efficiently Modeling Long Sequences with Structured State SpacesDeep Learning JP
This document summarizes a research paper on modeling long-range dependencies in sequence data using structured state space models and deep learning. The proposed S4 model (1) derives recurrent and convolutional representations of state space models, (2) improves long-term memory using HiPPO matrices, and (3) efficiently computes state space model convolution kernels. Experiments show S4 outperforms existing methods on various long-range dependency tasks, achieves fast and memory-efficient computation comparable to efficient Transformers, and performs competitively as a general sequence model.
NIPS KANSAI Reading Group #7: 逆強化学習の行動解析への応用Eiji Uchibe
Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning, Ecosphere,
Modeling sensory-motor decisions in natural behavior, PLoS Comp. Biol.
This document discusses self-supervised representation learning (SRL) for reinforcement learning tasks. SRL learns state representations by using prediction tasks as an auxiliary objective. The key ideas are: (1) SRL learns an encoder that maps observations to states using a prediction task like modeling future states or actions; (2) The learned state representations improve generalization and exploration in reinforcement learning algorithms; (3) Several SRL methods are discussed, including world models, inverse models, and causal infoGANs.
This document discusses self-supervised representation learning (SRL) for reinforcement learning tasks. SRL learns state representations by using prediction tasks as an auxiliary objective. The key ideas are: (1) SRL learns an encoder that maps observations to states using a prediction task like modeling future states or actions; (2) The learned state representations improve generalization and exploration in reinforcement learning algorithms; (3) Several SRL methods are discussed, including world models, inverse models, and causal infoGANs.
5. 発表���
● DQNに報酬�分布を�ち�んだ論文 ’A Distributional Perspective on
Reinforcement Learning’ を�に、最近���について��ます
● 発表に出てくる論文
○ Parametric Return Density Estimation for Reinforcement Learning
○ A Distributional Perspective on Reinforcement Learning
○ DISTRIBUTIONAL POLICY GRADIENTS
○ (THE REACTOR: A FAST AND SAMPLE-EFFICIENT ACTOR-CRITIC AGENT FOR
REINFORCEMENT LEARNING)
○ Distributional Reinforcement Learning with Quantile Regression
23. 結局、Wesserstein距離�どうなった�?
● 使ってない
● ‘We note that, while these algorithms appear unrelated to the Wasserstein
metric, recent work (Bellemare et al., 2017) hints at a deeper connection’らし
いけど、よくわからなかった
● こ�点�後続���で少し���ーされている