Shield Synthesis for Safe Reinforcement Learning

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=DUkqNJ-rwck


Duration: 32:10
749 views
19

Roderick Bloem (IAIK)
https://simons.berkeley.edu/talks/shield-synthesis-safe-reinforcement-learning
Synthesis of Models and Systems



Other Videos By Simons Institute for the Theory of Computing


2021-03-15A Brief Introduction to Theoretical Foundations of Machine Learning and Machine Teaching
2021-03-12United for Change: Deliberative Coalition Formation to Change the Status Quo
2021-03-11Are we aging well?
2021-03-11The Dawn of Computational Complexity Theory
2021-03-10Quantum Fault Tolerance with Flag Qubits | Quantum Colloquium
2021-03-09Beyond NP with Tractable Circuits
2021-03-08Synthesis of Functional Reactive Programs via a Reduction of Asynchronous Inputs to Lists
2021-03-08Synthesis of Coordination Programs from Linear Temporal Specifications
2021-03-08Synthesizing Approximate Implementations for Reactive Systems
2021-03-08Control Synthesis and its Magical Futures
2021-03-08Shield Synthesis for Safe Reinforcement Learning
2021-03-08TBA
2021-03-05Designing Agents' Preferences, Beliefs, and Identities
2021-03-04On Symmetry and Quantification: A New Approach to Verify Distributed Protocols
2021-03-04Progress in Symbolic Satisfiability Solving
2021-03-03Fault Tolerance with LDPC Codes | Quantum Colloquium
2021-03-02Embracing the Uncertainties
2021-03-01CounterExample Guided Inductive Synthesis Modulo Theories
2021-03-01Syntax-Guided Synthesis in SMT: A View from Inside the Solver
2021-03-01Data-Driven Inference of Representation Invariants
2021-03-01Neural Network guided Grammar Filtering For Syntax-Guided Synthesis


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Roderick Bloem
Synthesis of Models and Systems