Adversarial Reinforcement Learning for Observer Design in Autonomous Systems under Cyber Attacks

Sep 15, 2018

Abhishek Gupta, Zhaoyuan Yang

Sep 15, 2018

Abhishek Gupta, Zhaoyuan Yang

* 12 pages, 3 figures

**Click to Read Paper**

In this article, we provide and overview of what we consider to be some of the most pressing research questions facing the fields of artificial intelligence (AI) and computational intelligence (CI); with the latter focusing on algorithms that are inspired by various natural phenomena. We demarcate these questions using five unique Rs - namely, (i) rationalizability, (ii) resilience, (iii) reproducibility, (iv) realism, and (v) responsibility. Notably, just as air serves as the basic element of biological life, the term AIR5 - cumulatively referring to the five aforementioned Rs - is introduced herein to mark some of the basic elements of artificial life (supporting the sustained growth of AI and CI). A brief summary of each of the Rs is presented, highlighting their relevance as pillars of future research in this arena.

* 5 pages, 0 figures

* 5 pages, 0 figures

**Click to Read Paper**
Genetic Transfer or Population Diversification? Deciphering the Secret Ingredients of Evolutionary Multitask Optimization

Jul 19, 2016

Abhishek Gupta, Yew-Soon Ong

Jul 19, 2016

Abhishek Gupta, Yew-Soon Ong

* 7 pages, 6 figures

**Click to Read Paper**

A new Initial Centroid finding Method based on Dissimilarity Tree for K-means Algorithm

Jun 19, 2015

Abhishek Kumar, Suresh Chandra Gupta

Jun 19, 2015

Abhishek Kumar, Suresh Chandra Gupta

**Click to Read Paper**

Learning Actionable Representations with Goal-Conditioned Policies

Nov 19, 2018

Dibya Ghosh, Abhishek Gupta, Sergey Levine

Nov 19, 2018

Dibya Ghosh, Abhishek Gupta, Sergey Levine

**Click to Read Paper**

A Fixed Point Theorem for Iterative Random Contraction Operators over Banach Spaces

Apr 23, 2018

Abhishek Gupta, Rahul Jain, Peter Glynn

Consider a contraction operator $T$ over a Banach space $\mathcal X$ with a fixed point $x^\star$. Assume that one can approximate the operator $T$ by a random operator $\hat T^N$ using $N\in\mathbb{N}$ independent and identically distributed samples of a random variable. Consider the sequence $(\hat X^N_k)_{k\in\mathbb{N}}$, which is generated by $\hat X^N_{k+1} = \hat T^N(\hat X^N_k)$ and is a random sequence. In this paper, we prove that under certain conditions on the random operator, (i) the distribution of $\hat X^N_k$ converges to a unit mass over $x^\star$ as $k$ and $N$ goes to infinity, and (ii) the probability that $\hat X^N_k$ is far from $x^\star$ as $k$ goes to infinity can be made arbitrarily small by an appropriate choice of $N$. We also find a lower bound on the probability that $\hat X^N_k$ is far from $x^\star$ as $k\rightarrow \infty$. We apply the result to study probabilistic convergence of certain randomized optimization and value iteration algorithms.
Apr 23, 2018

Abhishek Gupta, Rahul Jain, Peter Glynn

* 35 pages

**Click to Read Paper**

Diversity is All You Need: Learning Skills without a Reward Function

Oct 09, 2018

Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, Sergey Levine

Oct 09, 2018

Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, Sergey Levine

* Videos and code for our experiments are available at: https://sites.google.com/view/diayn

**Click to Read Paper**

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Jun 18, 2018

YuXuan Liu, Abhishek Gupta, Pieter Abbeel, Sergey Levine

Jun 18, 2018

YuXuan Liu, Abhishek Gupta, Pieter Abbeel, Sergey Levine

* Accepted at ICRA 2018, Brisbane. YuXuan Liu and Abhishek Gupta had equal contribution

**Click to Read Paper**

Unsupervised Meta-Learning for Reinforcement Learning

Jun 12, 2018

Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine

Jun 12, 2018

Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine

**Click to Read Paper**

Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration

Mar 20, 2017

Abhishek Gupta, Clemens Eppner, Sergey Levine, Pieter Abbeel

Mar 20, 2017

Abhishek Gupta, Clemens Eppner, Sergey Levine, Pieter Abbeel

* Accepted at International Conference on Intelligent Robots and Systems(IROS) 2016. Pdf file updated for stylistic consistency

**Click to Read Paper**

Learning Dexterous Manipulation Policies from Experience and Imitation

Nov 15, 2016

Vikash Kumar, Abhishek Gupta, Emanuel Todorov, Sergey Levine

We explore learning-based approaches for feedback control of a dexterous five-finger hand performing non-prehensile manipulation. First, we learn local controllers that are able to perform the task starting at a predefined initial state. These controllers are constructed using trajectory optimization with respect to locally-linear time-varying models learned directly from sensor data. In some cases, we initialize the optimizer with human demonstrations collected via teleoperation in a virtual environment. We demonstrate that such controllers can perform the task robustly, both in simulation and on the physical platform, for a limited range of initial conditions around the trained starting state. We then consider two interpolation methods for generalizing to a wider range of initial conditions: deep learning, and nearest neighbors. We find that nearest neighbors achieve higher performance. Nevertheless, the neural network has its advantages: it uses only tactile and proprioceptive feedback but no visual feedback about the object (i.e. it performs the task blind) and learns a time-invariant policy. In contrast, the nearest neighbors method switches between time-varying local controllers based on the proximity of initial object states sensed via motion capture. While both generalization methods leave room for improvement, our work shows that (i) local trajectory-based controllers for complex non-prehensile manipulation tasks can be constructed from surprisingly small amounts of training data, and (ii) collections of such controllers can be interpolated to form more global controllers. Results are summarized in the supplementary video: https://youtu.be/E0wmO6deqjo
Nov 15, 2016

Vikash Kumar, Abhishek Gupta, Emanuel Todorov, Sergey Levine

* Initial draft for a journal submission

**Click to Read Paper**

Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution

Nov 17, 2017

Adam Å»ychowski, Abhishek Gupta, Jacek MaÅ„dziuk, Yew Soon Ong

Nov 17, 2017

Adam Å»ychowski, Abhishek Gupta, Jacek MaÅ„dziuk, Yew Soon Ong

**Click to Read Paper**

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost

Oct 14, 2018

Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine, Vikash Kumar

Oct 14, 2018

Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine, Vikash Kumar

* https://sites.google.com/view/deeprl-handmanipulation

**Click to Read Paper**

Automatically Composing Representation Transformations as a Means for Generalization

Jul 12, 2018

Michael B. Chang, Abhishek Gupta, Sergey Levine, Thomas L. Griffiths

Jul 12, 2018

Michael B. Chang, Abhishek Gupta, Sergey Levine, Thomas L. Griffiths

* Accepted to ICML workshop Neural Abstract Machines & Program Induction v2 2018

**Click to Read Paper**

Meta-Reinforcement Learning of Structured Exploration Strategies

Feb 20, 2018

Abhishek Gupta, Russell Mendonca, YuXuan Liu, Pieter Abbeel, Sergey Levine

Feb 20, 2018

Abhishek Gupta, Russell Mendonca, YuXuan Liu, Pieter Abbeel, Sergey Levine

**Click to Read Paper**

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

Mar 08, 2017

Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, Sergey Levine

Mar 08, 2017

Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, Sergey Levine

* Published as a conference paper at ICLR 2017

**Click to Read Paper**

Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer

Sep 22, 2016

Coline Devin, Abhishek Gupta, Trevor Darrell, Pieter Abbeel, Sergey Levine

Sep 22, 2016

Coline Devin, Abhishek Gupta, Trevor Darrell, Pieter Abbeel, Sergey Levine

* Under review at the International Conference on Robotics and Automation (ICRA) 2017

**Click to Read Paper**

Multiple View Reconstruction of Calibrated Images using Singular Value Decomposition

Nov 02, 2010

Ayan Chaudhury, Abhishek Gupta, Sumita Manna, Subhadeep Mukherjee, Amlan Chakrabarti

Nov 02, 2010

Ayan Chaudhury, Abhishek Gupta, Sumita Manna, Subhadeep Mukherjee, Amlan Chakrabarti

* In Proceedings of 4th IEEE international conference on Advanced Computing and Communication Technologies(ICACCT2010)

**Click to Read Paper**

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

Jun 26, 2018

Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, Giulia Vezzani, John Schulman, Emanuel Todorov, Sergey Levine

Jun 26, 2018

Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, Giulia Vezzani, John Schulman, Emanuel Todorov, Sergey Levine

* Accepted for presentation at Robotics: Science and Systems (RSS) 2018. Project page: https://sites.google.com/view/deeprl-dexterous-manipulation

**Click to Read Paper**

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

Jun 07, 2018

John D. Co-Reyes, YuXuan Liu, Abhishek Gupta, Benjamin Eysenbach, Pieter Abbeel, Sergey Levine

Jun 07, 2018

John D. Co-Reyes, YuXuan Liu, Abhishek Gupta, Benjamin Eysenbach, Pieter Abbeel, Sergey Levine

* Accepted at ICML 2018

**Click to Read Paper**