From a12db74b9841d5c42c3467d824e08d5e4eb329f4 Mon Sep 17 00:00:00 2001 From: Brandon Rozek Date: Thu, 17 Feb 2022 13:37:46 -0500 Subject: [PATCH] Updated research page --- content/research/_index.md | 48 +++++++++++++------ .../deepreinforcementlearning/_index.md | 16 ++++--- content/research/publications.md | 4 +- 3 files changed, 46 insertions(+), 22 deletions(-) diff --git a/content/research/_index.md b/content/research/_index.md index 027261c..b9a55bb 100644 --- a/content/research/_index.md +++ b/content/research/_index.md @@ -8,38 +8,58 @@ Description: A list of my research Projects **Broad Research Interests:** Automated Reasoning, Artificial Intelligence, Formal Methods ## Logic-Based AI -Working with [Dr. Selmer Bringsjord](https://homepages.rpi.edu/~brings/) and others in the [RAIR Lab](https://rair.cogsci.rpi.edu/) to design -and implement artificial intelligent agents whose behavior is verifiable -via chains of inference. More details coming soon... +Working with [Dr. Selmer Bringsjord](https://homepages.rpi.edu/~brings/) and others in the [RAIR Lab](https://rair.cogsci.rpi.edu/) to +design and implement artificial intelligent agents using computational logic. I'm particularly interested in: +- Explainability through verifiable chains of inference +- Defeasible reasoning under uncertainty +- Reasoning about agents and their cognitive states +- Automated planning under ethical constraints + ## Symbolic Methods for Cryptography -Worked with [Dr. Andrew Marshall](https://www.marshallandrew.net/) under an ONR grant in collaboration with University at Albany, Clarkson University, University of Texas at Dallas, and the Naval Research lab in order to automatically generated and verify cryptographic algorithms using symbolic (as opposed to computational) methods. +Working with [Dr. Andrew Marshall](https://www.marshallandrew.net/) and others in applying term reasoning within computational logic +towards cryptography. This collaboration was previously funded under an ONR grant. We are interested in applying techniques such +as unification and term rewriting to the following areas: +- Block Ciphers +- Secure Multi-party Computation +- Authentication +- Commitment Schemes + +Together we built [Symcollab](https://github.com/symcollab/CryptoSolve), a symbolic cryptographic analysis tool, and made it publically available on GitHub. I wrote the term algebra and rewrite libraries, and contributed to the mode of operation library and some unification algorithms. +I still help maintain the codebase, as well as contribute to our current work on Garbled Circuits. We previously presented our work +at [UNIF 2020](https://www3.risc.jku.at/publications/download/risc_6129/proceedings-UNIF2020.pdf#page=58) ([slides](/files/research/UNIF2020-Slides.pdf)), FROCOS 2021, and soon at WRLA 2022. + +I've written a few [Notes](termreasoning) about term reasoning. + +Collaborators: +- NRL: Catherine Meadows +- UMW: [Andrew Marshall]((https://www.marshallandrew.net/)), Veena Ravishankar +- UT Dallas: Serdar Erbatur +- SUNY Albany: [Paliath Narendran](https://www.cs.albany.edu/~dran/), Wei Du +- Clarkson University: [Christopher Lynch](https://people.clarkson.edu/~clynch/), Hai Lin -During that time period I built a free algebra library, rewrite library, parts of the crypto tool, and dabbled in Unification algorithms. You can check them out on [Github](https://github.com/symcollab/CryptoSolve). -Currently, I am an external collaborator who mainly helps maintain the codebase I started as well as contribute to our current work with Garbled Circuits. We presented our work at [UNIF 2020](https://www3.risc.jku.at/publications/download/risc_6129/proceedings-UNIF2020.pdf#page=58) ([slides](/files/research/UNIF2020-Slides.pdf)), FROCOS 2021, and have a couple other papers in the works. -Through my collaborators, I've learned about term reasoning and algebras. [[Notes]](termreasoning) ## Reinforcement Learning -**Deep Reinforcement Learning:** With [Dr. Ron Zacharski](http://zacharski.org/) I focused more on a particular instance of Reinforcement Learning where deep neural networks are used. During this time, I built out a Reinforcement Learning library written in PyTorch. This library helps me have a test bed for trying out different algorithms and attempts to create my own. +**Deep Reinforcement Learning:** With [Dr. Ron Zacharski](http://zacharski.org/) I focused on how to make deep reinforcement learning +algorithms more sample efficient. That is, how can we make it so that the RL agent learns more from every observation to make it so that +we achieve our goal faster. With that goal in mind, I built out a Reinforcement Learning library written in PyTorch to help benchmark +my ideas. -One particular problem I'm fascinated by is how to make Reinforcement Learning algoirthms more sample efficient. This means, how can we make it so that it learns more from every observation or make it so that we can achieve our goal quicker? *Links:* | | | | | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | -| [RL Library on Github](https://github.com/brandon-rozek/rltorch) | [Interactive Demonstrations Library](https://github.com/brandon-rozek/gyminteract) | [Honors Thesis](/files/research/honorsthesis.pdf) ([Eagle Scholar Entry](https://scholar.umw.edu/student_research/305/)) | -| [Honors Defense](/files/research/ExpeditedLearningInteractiveDemo.pptx) | [QEP Algorithm Slides](/files/research/QEP.pptx) | [More...](deepreinforcementlearning) | +| [RL Library on Github](https://github.com/brandon-rozek/rltorch) | [Interactive Demonstrations Library](https://github.com/brandon-rozek/gyminteract) | [Undergraduate Honors Thesis](/files/research/honorsthesis.pdf) ([Eagle Scholar Entry](https://scholar.umw.edu/student_research/305/)) | +| [Undergraduate Honors Defense](/files/research/ExpeditedLearningInteractiveDemo.pptx) | [QEP Algorithm Slides](/files/research/QEP.pptx) | [More...](deepreinforcementlearning) | **Reinforcement Learning:** Studied the fundamentals of reinforcement learning with [Dr. Stephen Davies](http://stephendavies.org/). We went over the fundamentals such as value functions, policy functions, how we can describe our environment as a markov decision processes, etc. -[Notes and Other Goodies](reinforcementlearning) - -[Github Code](https://github.com/brandon-rozek/ReinforcementLearning) +[Notes and Other Goodies](reinforcementlearning) / [Github Code](https://github.com/brandon-rozek/ReinforcementLearning) diff --git a/content/research/deepreinforcementlearning/_index.md b/content/research/deepreinforcementlearning/_index.md index da28df2..d2a8f57 100644 --- a/content/research/deepreinforcementlearning/_index.md +++ b/content/research/deepreinforcementlearning/_index.md @@ -3,20 +3,22 @@ Title: Deep Reinforcement Learning Description: Combining Reinforcement Learning with Deep Learning --- -In the Fall of 2019, I look at integrating demonstration data into a reinforcement learning algorithm in order to make it sample efficient. +I am interested in sample-efficient reinforcement learning. +That is, decreases the number of interactions an agent needs +with an environment to achieve some goal. In the Fall of 2019, +I approached this by integrating interactive demonstration +data into the optimized Deep Q-Networks algorithm. The results are positive and are heavily documented through the following: -[Honors Thesis](/files/research/honorsthesis.pdf) +[Undergraduate Honors Thesis](/files/research/honorsthesis.pdf) -[Honors Defense](/files/research/ExpeditedLearningInteractiveDemo.pptx) +[Undergraduate Honors Defense](/files/research/ExpeditedLearningInteractiveDemo.pptx) Thanks to my advisor Dr. Ron Zacharksi and my committee members for all their feedback on my work! -In the spring of 2019, under the guidance of Dr. Ron Zacharski I practiced several of the modern techniques used in Reinforcement Learning today. +The semester prior, I built a [reinforcement learning library](https://github.com/brandon-rozek/rltorch) with implementations of several popular papers. ([Semi-Weekly Progress](weeklyprogress)). -I facilitated my learning by creating a [reinforcement learning library](https://github.com/brandon-rozek/rltorch) with implementations of several popular papers. ([Semi-Weekly Progress](weeklyprogress)) - -I also presented my research (which involved creating an algorithm) at my school's research symposium. ([Slides](/files/research/QEP.pptx)) ([Abstract](abstractspring2019)) +I also presented at my school's research symposium. ([Slides](/files/research/QEP.pptx)) ([Abstract](abstractspring2019)) In the summer of 2019, I became interested in having the interactions with the environment be in a separate process. This inspired two different implementations, [ZeroMQ](https://github.com/brandon-rozek/zerogym) and [HTTP](https://github.com/brandon-rozek/gymhttp). Given the option, you should use the ZeroMQ implementation since it contains less communication overhead. diff --git a/content/research/publications.md b/content/research/publications.md index 6f05588..2b5801e 100644 --- a/content/research/publications.md +++ b/content/research/publications.md @@ -6,13 +6,15 @@ showthedate: false ## Papers -(Under Consideration) D Chichester, W Du, R Kauffman, H Lin, C Lynch, A Marshall, C Meadows, P Narendran, V Ravishankar, L Rovira, **B Rozek**. "CryptoSolve: A Tool for the Analysis of Cryptographic Modes of Operation", International Workshop on Rewriting Logic and its Applications, 2022. +(Under Consideration) **Brandon Rozek**, Michael Giancola, Selmer Bringsjord, Naveen Sundar Govindarajulu. "A Representation-and-Reasoning Framework for Testimony-Infused Automated Adjudicative Dynamic Multi-agent Reasoning & Decision-making", International Conference on Principles of Knowledge Representation and Reasoning, 2022. [Hai Lin, Christopher Lynch, Andrew M. Marshall, Catherine A. Meadows, Paliath Narendran, Veena Ravishankar, **Brandon Rozek**. "Algorithmic Problems in the Symbolic Approach to the Verification of Automatically Synthesized Cryptosystems", International Symposium on Frontiers of Combining Systems, 2021.](https://link.springer.com/chapter/10.1007/978-3-030-86205-3_14) ## Workshops +D Chichester, W Du, R Kauffman, H Lin, C Lynch, A Marshall, C Meadows, P Narendran, V Ravishankar, L Rovira, **B Rozek**. "CryptoSolve: Towards a Tool for the Symbolic Analysis of Cryptographic Algorithms", International Workshop on Rewriting Logic and its Applications, 2022. + [Andrew M Marshall, Catherine A Meadows, Paliath Narendran, Veena Ravishankar, **Brandon Rozek**. "Algorithmic Problems in Synthesized Cryptosystems", International Workshop on Unification, 2020.](https://www3.risc.jku.at/publications/download/risc_6129/proceedings-UNIF2020.pdf#page=58)