San Francisco, California, United States
Contact Info
2K followers
500+ connections
Experience & Education
Publications
-
Composing Complex Skills by Learning Transition Policies with Proximity Reward Induction
International Conference on Learning Representations (ICLR)
Intelligent creatures acquire complex skills by exploiting previously learned skills and learning to transition between them. To empower machines with this ability, we propose transition policies which effectively connect primitive skills to perform sequential tasks without handcrafted rewards. To effectively train our transition policies, we introduce proximity predictors which induce rewards gauging proximity to suitable initial states for the next skill. The proposed method is evaluated on a…
Intelligent creatures acquire complex skills by exploiting previously learned skills and learning to transition between them. To empower machines with this ability, we propose transition policies which effectively connect primitive skills to perform sequential tasks without handcrafted rewards. To effectively train our transition policies, we introduce proximity predictors which induce rewards gauging proximity to suitable initial states for the next skill. The proposed method is evaluated on a diverse set of experiments for continuous control in both bi-pedal locomotion and robotic arm manipulation tasks in MuJoCo. We demonstrate that transition policies enable us to effectively learn complex tasks and the induced proximity reward computed using the initiation predictor improves training efficiency.
-
Neural Program Synthesis from Diverse Demonstration Videos
International Conference on Machine Learning (ICML)
Interpreting decision making logic in demonstration videos is key to collaborating with and mimicking humans. To empower machines with this ability, we propose a neural program synthesizer that is able to explicitly synthesize underlying programs from behaviorally diverse and visually complicated demonstration videos. We introduce a summarizer module as part of our model to improve the network’s ability to integrate multiple demonstrations varying in behavior. We also employ a multi-task…
Interpreting decision making logic in demonstration videos is key to collaborating with and mimicking humans. To empower machines with this ability, we propose a neural program synthesizer that is able to explicitly synthesize underlying programs from behaviorally diverse and visually complicated demonstration videos. We introduce a summarizer module as part of our model to improve the network’s ability to integrate multiple demonstrations varying in behavior. We also employ a multi-task objective to encourage the model to learn meaningful intermediate representations for end-to-end training. We show that our model is able to reliably synthesize underlying programs as well as capture diverse behaviors exhibited in demonstrations. Website and code at https://shaohua0116.github.io/demo2program.
-
pH-susceptibility of HLA-DO tunes DO/DM ratios to regulate HLA-DM catalytic activity
Scientific Reports (Nature)
Projects
-
Learning Car
- Present
Implemented reinforcement learning (RL) in a robotic car. Used the goBetwino API to connect an Arduino Mega microcontroller to RL program which received car state info from the serial port.
Other creatorsSee project
Honors & Awards
-
Summa Cum Laude
University of Southern California
-
Additional Honors
-
Presidential Scholarship (USC)
National AP Scholar - Computer Science, Calculus BC, Chemistry, Spanish, World History, U.S. History, Biology, Microeconomics, Macroeconomics, Psychology, Environmental Science, Statistics, Physics C: Mechanics, Physics C: Electricity and Magnetism
National Merit Finalist
2015 Intel STS Semifinalist
Intel International Science and Engineering Fair (ISEF) - 2nd place (2014) in Biochemistry
First place at Synopsys Championship Fair (2014) & Grand…Presidential Scholarship (USC)
National AP Scholar - Computer Science, Calculus BC, Chemistry, Spanish, World History, U.S. History, Biology, Microeconomics, Macroeconomics, Psychology, Environmental Science, Statistics, Physics C: Mechanics, Physics C: Electricity and Magnetism
National Merit Finalist
2015 Intel STS Semifinalist
Intel International Science and Engineering Fair (ISEF) - 2nd place (2014) in Biochemistry
First place at Synopsys Championship Fair (2014) & Grand Prize – Best of Biological Sciences
n+1 award at Synopsys
Other similar profiles
-
Allan Bishop
Connect -
Allen Naliath
CS AI at Stanford | President and Founder, Stanford Startup Society | Prev @ Amazon Robotics
Connect -
George Sivulka
Connect -
Kyle Rentschler
Connect -
Nate Schickler
Experienced software engineer dedicated to building meaningful software projects with cutting-edge technologies.
Connect -
Tanvi Deshpande
Connect -
Tim Lupo
Connect -
Advait Paliwal
Connect -
Nikhil Suresh
Connect -
Ammar Husain
Connect
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Sriram Somasundaram
-
Sriram Somasundaram
Building strong teams and Mentoring future leaders
-
Sriram Somasundaram
Regional Sales Director for Tamilnadu & Kerala | Sales Presentations, Online Marketing
-
Sriram Somasundaram
Quality Services Manager at Amazon Development Center
-
Sriram Somasundaram
Transforming data into value • Experienced Product Manager • Specialties: Market Analysis, Product Strategy
17 others named Sriram Somasundaram are on LinkedIn
See others named Sriram Somasundaram