paper-with-me

Papers

Predictive Information Accelerates Learning in RL

2020-07-24 · NeurIPS 2020 12 · Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee, John Canny, Sergio Guadarrama

The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. To test our hypothesis, we train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics using a contrastive version of the Conditional Entropy Bottleneck (CEB) objective. We refer to these as Predictive Information SAC (PI-SAC) agents. We show that PI-SAC agents can substantially improve sample efficiency over challenging baselines on tasks from the DM Control suite of continuous control environments. We evaluate PI-SAC agents by comparing against uncompressed PI-SAC agents, other compressed and uncompressed agents, and SAC agents directly trained from pixels. Our implementation is given on GitHub.

📄 PDF Abstract BibTeX arXiv:2007.12401

Code (1)

google-research/pisac 공식 구현 tf

Tasks

continuous-controlContinuous Control

Methods 이 논문이 사용한 방법론

Dilated Convolution 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
SAC 설명 없음

Similar Papers 제목 키워드 기반

Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity

2024-06-25 · Yuji Byun, Jaeho Lee

Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of language models, significantly reducing computational costs. By adjusting ranks for each client, federated …

Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process

2024-03-25 · Kevin S. Miller, Adam J. Thorpe, Ufuk Topcu

We present an active learning algorithm for learning dynamics that leverages side information by explicitly incorporating prior domain knowledge into the sampling process. Our proposed algorithm guides the exploration to…

Active LearningMuJoCo

Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization

2026-02-19 · Sumedh Rasal arxiv

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curricul…

Scalable Model Selection for Belief Networks

2017-12-01 · NeurIPS 2017 12 · Zhao Song, Yusuke Muraoka, Ryohei Fujimaki, Lawrence Carin

We propose a scalable algorithm for model selection in sigmoid belief networks (SBNs), based on the factorized asymptotic Bayesian (FAB) framework. We derive the corresponding generalized factorized information criterion…

modelModel Selection

Towards Practical Lossless Neural Compression for LiDAR Point Clouds

2026-03-26 · Pengpeng Yu, Haoran Li, Runqing Jiang, Dingquan Li 외 arxiv

LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of exist…

Point Clouds