<--- Back to Details
First PageDocument Content
Artificial intelligence / Machine learning algorithms / Statistical theory / Probability and statistics / Reinforcement learning / Q-learning / Partially observable Markov decision process / Entropy / OpenAI / Cross entropy / DQN
Date: 2016-12-09 10:01:25
Artificial intelligence
Machine learning algorithms
Statistical theory
Probability and statistics
Reinforcement learning
Q-learning
Partially observable Markov decision process
Entropy
OpenAI
Cross entropy
DQN

The Nuts and Bolts of Deep RL Research John Schulman December 9th, 2016 Outline

Add to Reading List

Source URL: rll.berkeley.edu

Download Document from Source Website

File Size: 311,09 KB

Share Document on Facebook

Similar Documents

Cross-diffusion systems with entropy structure Ansgar J¨ ungel (TU Vienna) Cross-diffusion systems describe the diffusive interaction of multi-species systems. Examples include multi-species population dynamics, cell bi

Cross-diffusion systems with entropy structure Ansgar J¨ ungel (TU Vienna) Cross-diffusion systems describe the diffusive interaction of multi-species systems. Examples include multi-species population dynamics, cell bi

DocID: 1uigJ - View Document

Multifidelity preconditioning of the cross-entropy method for rare event simulation and failure probability estimation

Multifidelity preconditioning of the cross-entropy method for rare event simulation and failure probability estimation

DocID: 1tGD9 - View Document

Motivations  PRNG Security Model Java SecureRandom Analysis

Motivations PRNG Security Model Java SecureRandom Analysis

DocID: 1rmDv - View Document

PDF Document

DocID: 1r2P8 - View Document

Finding Progression Stages in Time-evolving Event Sequences Jaewon Yang†∗ Julian McAuley† Jure Leskovec† Paea LePendu‡ Nigam Shah‡ † Computer Science, Stanford University, {jayang, jmcauley, jure}@cs.stanfo

Finding Progression Stages in Time-evolving Event Sequences Jaewon Yang†∗ Julian McAuley† Jure Leskovec† Paea LePendu‡ Nigam Shah‡ † Computer Science, Stanford University, {jayang, jmcauley, jure}@cs.stanfo

DocID: 1qo0s - View Document