About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

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

6 Nov 2018ShangtongZhang/DeepRL

In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning.

CONTINUOUS CONTROL VALUE PREDICTION

Value Prediction Network

NeurIPS 2017 werner-duvaud/muzero-general

This paper proposes a novel deep reinforcement learning (RL) architecture, called Value Prediction Network (VPN), which integrates model-free and model-based RL methods into a single neural network.

ATARI GAMES VALUE PREDICTION

TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning

ICLR 2018 oxwhirl/treeqn

To address these challenges, we propose TreeQN, a differentiable, recursive, tree-structured model that serves as a drop-in replacement for any value function network in deep RL with discrete actions.

ATARI GAMES VALUE PREDICTION

Code Prediction by Feeding Trees to Transformers

30 Mar 2020facebookresearch/code-prediction-transformer

We provide comprehensive experimental evaluation of our proposal, along with alternative design choices, on a standard Python dataset, as well as on a Python corpus internal to Facebook.

TYPE PREDICTION VALUE PREDICTION SOFTWARE ENGINEERING

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

KDD 2020 Roytsai27/Dual-Attentive-Tree-aware-Embedding

Intentional manipulation of invoices that lead to undervaluation of trade goods is the most common type of customs fraud to avoid ad valorem duties and taxes.

FRAUD DETECTION MULTI-TARGET REGRESSION VALUE PREDICTION

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

9 Jun 2020elisim/piven

Improving the robustness of neural nets in regression tasks is key to their application in multiple domains.

PREDICTION INTERVALS VALUE PREDICTION

Spatial Action Maps for Mobile Manipulation

20 Apr 2020jimmyyhwu/spatial-action-maps

Typical end-to-end formulations for learning robotic navigation involve predicting a small set of steering command actions (e. g., step forward, turn left, turn right, etc.)

Q-LEARNING VALUE PREDICTION