scholarly journals A Critical Period for Robust Curriculum‐Based Deep Reinforcement Learning of Sequential Action in a Robot Arm

2022 ◽  
Author(s):  
Roy de Kleijn ◽  
Deniz Sen ◽  
George Kachergis
Keyword(s):  
Reinforcement Learning ◽  
Critical Period ◽  
Robot Arm ◽  
Sequential Action

EEG-Induced Autonomous Game-Teaching to a Robot Arm by Human Trainers Using Reinforcement Learning

2021 ◽  
pp. 1-1
Author(s):  
Reshma Kar ◽  
Lidia Ghosh ◽  
Amit Konar ◽  
Aruna Chakraborty ◽  
Atulya K. Nagar
Keyword(s):  
Reinforcement Learning ◽  
Robot Arm

scholarly journals Model-Based Reinforcement Learning in Multiagent Systems with Sequential Action Selection

2011 ◽  
Vol E94-D (2) ◽  
pp. 255-263 ◽  
Author(s):  
Ali AKRAMIZADEH ◽  
Ahmad AFSHAR ◽  
Mohammad Bagher MENHAJ ◽  
Samira JAFARI
Keyword(s):  
Reinforcement Learning ◽  
Multiagent Systems ◽  
Action Selection ◽  
Sequential Action ◽  
Model Based

scholarly journals Gamma-Nets: Generalizing Value Estimation over Timescale

2020 ◽  
Vol 34 (04) ◽  
pp. 5717-5725
Author(s):  
Craig Sherstan ◽  
Shibhansh Dohare ◽  
James MacGlashan ◽  
Johannes Günther ◽  
Patrick M. Pilarski
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
A Priori ◽  
Predictive Ability ◽  
Representation Learning ◽  
Robot Arm ◽  
Function Estimation ◽  
Temporal Abstraction ◽  
Long Time ◽  
Function Approximator

Temporal abstraction is a key requirement for agents making decisions over long time horizons—a fundamental challenge in reinforcement learning. There are many reasons why value estimates at multiple timescales might be useful; recent work has shown that value estimates at different time scales can be the basis for creating more advanced discounting functions and for driving representation learning. Further, predictions at many different timescales serve to broaden an agent's model of its environment. One predictive approach of interest within an online learning setting is general value function (GVFs), which represent models of an agent's world as a collection of predictive questions each defined by a policy, a signal to be predicted, and a prediction timescale. In this paper we present Γ-nets, a method for generalizing value function estimation over timescale, allowing a given GVF to be trained and queried for arbitrary timescales so as to greatly increase the predictive ability and scalability of a GVF-based model. The key to our approach is to use timescale as one of the value estimator's inputs. As a result, the prediction target for any timescale is available at every timestep and we are free to train on any number of timescales. We first provide two demonstrations by 1) predicting a square wave and 2) predicting sensorimotor signals on a robot arm using a linear function approximator. Next, we empirically evaluate Γ-nets in the deep reinforcement learning setting using policy evaluation on a set of Atari video games. Our results show that Γ-nets can be effective for predicting arbitrary timescales, with only a small cost in accuracy as compared to learning estimators for fixed timescales. Γ-nets provide a method for accurately and compactly making predictions at many timescales without requiring a priori knowledge of the task, making it a valuable contribution to ongoing work on model-based planning, representation learning, and lifelong learning algorithms.

Reinforcement learning strategies for sequential action learning

2009 ◽  
Vol 65 ◽  
pp. S236
Author(s):  
Alan Fermin ◽  
Yoshida Takehiko ◽  
Saori Tanaka ◽  
Makoto Ito ◽  
Junichiro Yoshimoto ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Learning Strategies ◽  
Action Learning ◽  
Sequential Action
Sign in / Sign up

Export Citation Format

Share Document