Action Robust Reinforcement Learning and Applications in Continuous - PowerPoint PPT Presentation

Oct 20, 2023 •414 likes •502 views

Action Robust Reinforcement Learning and Applications in Continuous Control Chen Tessler , Yonathan Efroni and Shie Mannor *equal contribution Poster #272 Action Robust Reinforcement Learning and Applications in Continuous Control Robust MDPs

Action Robust Reinforcement Learning and Applications in Continuous Control Chen Tessler *, Yonathan Efroni* and Shie Mannor *equal contribution Poster #272
Action Robust Reinforcement Learning and Applications in Continuous Control Robust MDPs Important model, yet not feasible in practical applications.
Action Robust Reinforcement Learning and Applications in Continuous Control Action Robustness in Robotics Abrupt disturbances Model uncertainty
Action Robust Reinforcement Learning and Applications in Continuous Control Action Robust MDPs AR-MDPs are a special case of RMDPs, which consider uncertainty in the performed action.
Action Robust Reinforcement Learning and Applications in Continuous Control Update adversary Algorithm Find optimal towards the actor policy 1-step greedy policy Evaluate joint policy Theorem 1. This procedure converges to the Nash equilibrium.
Action Robust Reinforcement Learning and Applications in Continuous Control Results Baseline Ours( 𝛽 =1)
Action Robust Reinforcement Learning and Applications in Continuous Control Conclusions - Robustness enables coping with uncertainty and transfer to unseen domains - A gradient based approach for robust reinforcement learning with convergence guarantees - Does not require explicit definition of the uncertainty set - Application to Deep RL
Action Robust Reinforcement Learning and Applications in Continuous Control Come visit @ Poster #272

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B. Temporal Difference Reinforcement Learning C. PVLV Model D. Cerebellum and Error-driven Learning 2/23/18 COSC 494/594 CCN 2 Sensory-Motor Loop

790 views • 56 slides

Reinforcement Learning for Continuous State and Action Spaces Gradient Methods 1 MACHINE LEARNING

MACHINE LEARNING 2012 MACHINE LEARNING TECHNIQUES AND APPLICATIONS Reinforcement Learning for Continuous State and Action Spaces Gradient Methods 1 MACHINE LEARNING 2012 Reinforcement Learning (RL) Supervised Learning Unsupervised

777 views • 51 slides

Reinforcement learning with restrictions on the action set Mario Bravo Universidad de Chile

Reinforcement learning with restrictions on the action set Reinforcement learning with restrictions on the action set Mario Bravo Universidad de Chile Joint work with Mathieu Faure (AMSE-GREQAM) Reinforcement learning with restrictions on the

976 views • 68 slides

Foundations of Machine Learning Reinforcement Learning Reinforcement Learning Agent exploring

Foundations of Machine Learning Reinforcement Learning Reinforcement Learning Agent exploring environment. Interactions with environment: action state Agent Environment reward Problem: find action policy that maximizes cumulative reward

828 views • 66 slides

Reinforcement Learning: How Does It Work? We detect a state Reinforcement Learning We choose an

1 Reinforcement Learning: How Does It Work? We detect a state Reinforcement Learning We choose an action Lecture 2 We get a reward Gillian Hayes Our aim is to learn a policy what action to choose in what state to get maximum reward 11th

641 views • 5 slides

Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

1 Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5 Environment Dynamics Gillian Hayes Components of a Problem 18th January 2007 Values and Action Values, V and Q Optimal Policies

109 views • 7 slides

Global plan Reinforcement learning I: prediction classical conditioning

Global plan Reinforcement learning I: prediction classical conditioning dopamine Reinforcement learning II: Reinforcement learning II: dynamic programming; action selection Pavlovian misbehaviour vigor

584 views • 46 slides

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement learning? Agent/Actor + Action + Environment + State + Reward How does reinforcement learning work?

792 views • 31 slides

Reproducible, Reusable, and Robust Reinforcement Learning Joelle Pineau Facebook AI Research,

Reproducible, Reusable, and Robust Reinforcement Learning Joelle Pineau Facebook AI Research, Montreal School of Computer Science, McGill University Neural Information Processing Systems (NeurIPS) December 5, 2018 Reproducibility refers to

979 views • 58 slides

Kernel-based Reinforcement Learning in Robust Markov Decision Processes Shiau Hong Lim, Arnaud

Kernel-based Reinforcement Learning in Robust Markov Decision Processes Shiau Hong Lim, Arnaud Autef Motivation Robust Markov Decision Process (MDP) framework Tackle model mismatch and parameter uncertainty Previously, for state

520 views • 13 slides

Fingerprint Policy Optimisation for Robust Reinforcement Learning Supratik Paul, Michael A.

Poster #50 Fingerprint Policy Optimisation for Robust Reinforcement Learning Supratik Paul, Michael A. Osborne, Shimon Whiteson This project has received funding from the European Research Council (ERC) under the European Unions Horizon 2020

385 views • 25 slides

Learning Action Representations for Reinforcement Learning Georgios Scott Yash James Philip

Learning Action Representations for Reinforcement Learning Georgios Scott Yash James Philip Theocharous Jordan Chandak Kostas Thomas Reinforcement Learning Problem Statement Thousands of possible actions! Problem Statement Thousands of

611 views • 31 slides

Imitation Learning Spring 2019, CMU 10-403 Katerina Fragkiadaki Reinforcement learning Agent

Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Imitation Learning Spring 2019, CMU 10-403 Katerina Fragkiadaki Reinforcement learning Agent state reward action S t R t A t R t+ 1 Environment S t+ 1

1.07k views • 52 slides

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

Introduction to Reinforcement Learning RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem Inside an RL agent Temporal difference learning Many faces of Reinforcement Learning What is

551 views • 35 slides

Guidelines for Action Space Definition in Reinforcement Learning-based Traffic Signal Control

Guidelines for Action Space Definition in Reinforcement Learning-based Traffic Signal Control Systems Maxime Trca, Julian Garbiso, Dominique Barth October 15, 2020 Outline I - Reinforcement Learning Applied to Traffic Signal Control II -

189 views • 16 slides

Reinforcement Learning A (almost) quick (and very incomplete) introduction Slides from David

Reinforcement Learning A (almost) quick (and very incomplete) introduction Slides from David Silver, Dan Klein, Mausam, Dan Weld Reinforcement Learning At each time step t : Agent executes an action A t Environment emits a reward Rt

1.1k views • 71 slides

Dynamic Graph Algorithms Christian Wulff-Nilsen University of Copenhagen November 14 , 2019 1 /

Dynamic Graph Algorithms Christian Wulff-Nilsen University of Copenhagen November 14 , 2019 1 / 21 Graph algorithms and data structures 2 / 21 Graph algorithms and data structures Graphs and graph problems are everywhere: 2 / 21 Graph

1.53k views • 110 slides

for Information Gathering with Adversarial Traffic Stefan Dobrev, Slovak Academy of Sciences,

Optimal Local Buffer Management for Information Gathering with Adversarial Traffic Stefan Dobrev, Slovak Academy of Sciences, Slovakia Manuel Lafond, University of Ottawa, Canada Lata Narayanan, Concordia University, Canada Jaroslav Opatrny,

573 views • 55 slides

MA/CSSE 474 Theory of Computation Pumping Theorem Examples Decision Problems Your Questions?

3/29/2018 MA/CSSE 474 Theory of Computation Pumping Theorem Examples Decision Problems Your Questions? Previous class days' material Reading Assignments HW 7 or 8 problems Anything else 1 3/29/2018 474 Difficulty

197 views • 9 slides

CS573 Data Privacy and Security Secure Multiparty Computation General Constructions Li Xiong

CS573 Data Privacy and Security Secure Multiparty Computation General Constructions Li Xiong Last Lecture Symmetric & Public key encryption Secure Multiparty Computations Problem and security definitions General constructions

846 views • 55 slides

A New Framework for RFID Privacy Robert H. Deng, Yingjiu Li, Moti Yung, Yunlei Zhao ESORICS 2010

A New Framework for RFID Privacy Robert H. Deng, Yingjiu Li, Moti Yung, Yunlei Zhao ESORICS 2010 Outline Introduction. Model of RFID Systems. Adaptive Completeness and Mutual Authentication. zk-Privacy: Formulation, Clarifications

456 views • 35 slides

Time Measurement Threatens Privacy-Friendly RFID Authentication Protocols Gildas Avoine 1 , Iwen

Time Measurement Threatens Privacy-Friendly RFID Authentication Protocols Gildas Avoine 1 , Iwen Coisel 2 and Tania Martin 1 1: Information Security Group - Universit e Catholique de Louvain 2: Crypto Group - Universit e Catholique de

605 views • 24 slides

Quantum query complexity and the adversary bound Part II: Learning graphs Alexander Belov

Quantum query complexity and the adversary bound Part II: Learning graphs Alexander Belov University of Latvia 22nd EWSCS, 5-10 March 2017, Palmse 1 / 35 Learning graphs Dual Adversary Certificate Structure Examples Idea Construction

639 views • 44 slides

masterclass 8 th October 2019 Claire Morrissey Senior Associate www.shoosmiths.co.uk Workshop 1

IOSH Investigations masterclass 8 th October 2019 Claire Morrissey Senior Associate www.shoosmiths.co.uk Workshop 1 Being Interviewed by the HSE and the Police Who are Shoosmiths? What do we do? Purpose and format of the

528 views • 11 slides