Deep Reinforcement Learning for Robotic Manipulation-The state of the art

by   Smruti Amarjyoti, et al.

The focus of this work is to enumerate the various approaches and algorithms that center around application of reinforcement learning in robotic ma- ]]nipulation tasks. Earlier methods utilized specialized policy representations and human demonstrations to constrict the policy. Such methods worked well with continuous state and policy space of robots but failed to come up with generalized policies. Subsequently, high dimensional non-linear function approximators like neural networks have been used to learn policies from scratch. Several novel and recent approaches have also embedded control policy with efficient perceptual representation using deep learning. This has led to the emergence of a new branch of dynamic robot control system called deep r inforcement learning(DRL). This work embodies a survey of the most recent algorithms, architectures and their implementations in simulations and real world robotic platforms. The gamut of DRL architectures are partitioned into two different branches namely, discrete action space algorithms(DAS) and continuous action space algorithms(CAS). Further, the CAS algorithms are divided into stochastic continuous action space(SCAS) and deterministic continuous action space(DCAS) algorithms. Along with elucidating an organ- isation of the DRL algorithms this work also manifests some of the state of the art applications of these approaches in robotic manipulation tasks.


page 11

page 15


Particle-Based Adaptive Discretization for Continuous Control using Deep Reinforcement Learning

Learning controls in high-dimensional continuous action spaces, such as ...

How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?

Deep Reinforcement Learning is a promising paradigm for robotic control ...

Policy Search in Continuous Action Domains: an Overview

Continuous action policy search, the search for efficient policies in co...

Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies

Researchers have demonstrated that Deep Reinforcement Learning (DRL) is ...

Pretty darn good control: when are approximate solutions better than approximate models

Existing methods for optimal control struggle to deal with the complexit...

Partial Observability during DRL for Robot Control

Deep Reinforcement Learning (DRL) has made tremendous advances in both s...

Verifying Learning-Based Robotic Navigation Systems

Deep reinforcement learning (DRL) has become a dominant deep-learning pa...

Please sign up or login with your details

Forgot password? Click here to reset