computer-vision

Value prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in value-prediction

Trend

Dataset

Best Model

Actions

Py150

Libraries

i

Use these libraries to find value-prediction models and implementations

Datasets

No datasets available.

Subtasks

Body Mass Index (BMI) Prediction

Most implemented papers

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble

Hyun Oh Song, Gaon An, Seungyong Moon, Jang-Hyun Kim•Sun Oct 03 2021

It is found that it is possible to substantially outperform existing offline RL methods on various tasks by simply increasing the number of Q-networks along with the clipped Q-learning and proposing an ensemble-diversified actor-critic algorithm that reduces the number of required ensemble networks down to a tenth compared to the naive ensemble.

351

Content

0

Paper Graph

Value Prediction Network

Honglak Lee, Junhyuk Oh, Satinder Singh•Mon Jul 10 2017

This paper proposes a novel deep reinforcement learning architecture, called Value Prediction Network (VPN), which integrates model-free and model-based RL methods into a single neural network, which outperforms Deep Q-Network on several Atari games even with short-lookahead planning.

346 0

Paper Graph

ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search

Shangtong Zhang, Hao Chen, Hengshuai Yao•Mon Nov 05 2018

This paper proposes an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning, and forms ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options.

26 0

Paper Graph

Code Prediction by Feeding Trees to Transformers

Seohyun Kim, Jinman Zhao, Yuchi Tian, S. Chandra•Sun Mar 29 2020

This work shows that by making the Transformer architecture aware of the syntactic structure of code, it increases the margin by which a Transformer-based system outperforms previous systems, and advances the state-of-the-art in the accuracy of code prediction (next token prediction) used in autocomplete systems.

238 0

Paper Graph

timeXplain - A Framework for Explaining the Predictions of Time Series Classifiers

Patrick Schäfer, Felix Mujkanovic, Vanja Doskoč, Martin Schirneck, T. Friedrich•Tue Jul 14 2020

The timeXplain framework is employed in a large-scale experimental comparison of several state-of-the-art time series classifiers and similarities between seemingly distinct classification concepts such as residual neural networks and elastic ensembles are discovered.

28 0

Paper Graph

DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection

Sundong Kim, Yu-Che Tsai, Karandeep Singh, Yeonsoo Choi, Etim Ibok, Cheng-Te Li, Meeyoung Cha•Sun Jul 05 2020

DATE, a model of Dual-task Attentive Tree-aware tree-aware Embedding, is proposed, to classify and rank illegal trade flows that contribute the most to the overall customs revenue when caught.

29 0

Paper Graph

PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction

L. Rokach, Gilad Katz, Eli Simhayev•Mon Jun 08 2020

PIVEN is presented, a deep neural network for producing both a PI and a prediction of specific values, and shows that its approach produces tighter uncertainty bounds than the current state-of-the-art approach for producing PIs, while managing to maintain comparable performance to the state of the art approach for specific value-prediction.

14 0

Paper Graph

Learning State Representations from Random Deep Action-conditional Predictions

Satinder Singh, Zeyu Zheng, Vivek Veeriah, Risto Vuorio, Richard L. Lewis•Mon Feb 08 2021

This work shows that random deep action-conditional predictions when used as auxiliary tasks yield state representations that produce control performance competitive with state-of-the-art hand-crafted auxiliary tasks like value prediction, pixel control, and CURL in both Atari and DeepMind Lab tasks.

6 0

Paper Graph

Spatial Action Maps for Mobile Manipulation

Andy Zeng, Shuran Song, Johnny Lee, T. Funkhouser, Xingyuan Sun, Jimmy Wu, S. Rusinkiewicz•Sun Apr 19 2020

This work presents "spatial action maps," in which the set of possible actions is represented by a pixel map (aligned with the input image of the current state), where each pixel represents a local navigational endpoint at the corresponding scene location.

82 0

Paper Graph

Adding a benchmark result helps the community track progress.