Exploration by Distributional Reinforcement Learning

05/04/2018
by   Yunhao Tang, et al.
1

We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous methods in exploration. We also derive a practical algorithm that achieves efficient exploration on challenging control tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/13/2019

Distributional Reinforcement Learning for Efficient Exploration

In distributional reinforcement learning (RL), the estimated distributio...
research
08/18/2011

Feature Reinforcement Learning In Practice

Following a recent surge in using history-based methods for resolving pe...
research
11/29/2020

Cluster Based Deep Contextual Reinforcement Learning for top-k Recommendations

Rapid advancements in the E-commerce sector over the last few decades ha...
research
02/17/2020

Langevin DQN

Algorithms that tackle deep exploration – an important challenge in rein...
research
04/23/2018

Distributed Distributional Deterministic Policy Gradients

This work adopts the very successful distributional perspective on reinf...
research
11/15/2021

Piano Fingering with Reinforcement Learning

Hand and finger movements are a mainstay of piano technique. Automatic F...
research
04/13/2018

Smooth and Efficient Policy Exploration for Robot Trajectory Learning

Many policy search algorithms have been proposed for robot learning and ...

Please sign up or login with your details

Forgot password? Click here to reset