Reinforcement Learning
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim
Humans make effective use of prior knowledge to acquire new skills rapidly.
A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation
Xueying Bai, Jian Guan, Hongning Wang
Neural Information Processing Systems http://nips.cc/
the value of generative adversarial training for model-based reinforcement learning (RL) with offline data, especially
First, we sincerely thank all reviewers for their thoughtful comments and suggestions. We will report the variance and statistical significance of our empirical results in our revision. These shed light on the approach's effectiveness as an online recommender. These two factors help control bias in value estimation for model-based RL. Please refer to Line 9-15 for our responses to possible new empirical evaluations.
Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning
Harsh Gupta, R. Srikant, Lei Ying
Neural Information Processing Systems http://nips.cc/
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
Neural Information Processing Systems http://nips.cc/
Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory
Neural Information Processing Systems http://nips.cc/
sponse addressing one common point raised by Reviewer 1 and Reviewer 3 regarding how to handle the case where 2 null
We thank all the reviewers for their careful feedback and will revise our paper accordingly. Such a fact is presented in the classic paper "An analysis of temporal-difference learning with function Similar facts can be found for other TD algorithms (e.g. Reviewer 1 is correct in that a discount factor is needed. Now we address specific reviewer comments below. A reference for this is the classic paper "An Finally, the "-" sign in Line 213 is due to the Hurwtiz assumption.
Disentangled behavioural representations
Amir Dezfouli, Hassan Ashtiani, Omar Ghattas, Richard Nock, Peter Dayan, Cheng Soon Ong
Unfortunately, the parameter and latent activity spaces of RNNs are generally high-dimensional and uninterpretable, making it hard to use them to study individual differences.
A neurally plausible model learns successor representations in partially observable environments
However, it is not clear how such representations might be learned and computed in partially observed, noisy environments. Here, we introduce a neurally plausible model using distributional successor features, which builds on the distributed distributional code for the representation and computation of uncertainty, and which allows for efficient value function computation in partially observed environments via the successor representation.