hacking reinforcement learning
play

Hacking Reinforcement Learning Guillem Duran Ballester Guillemdb - PowerPoint PPT Presentation

Sep 25, 2023 •337 likes •960 views

Hacking Reinforcement Learning Guillem Duran Ballester Guillemdb @Miau_DB A tale about hacking AI-Corp Hacking RL 1. Information gathering 2. Scanning 3. Exploitation & privilege escalation 4. Maintaining access & covering tracks

  1. Hacking Reinforcement Learning Guillem Duran Ballester Guillemdb @Miau_DB

  2. A tale about hacking AI-Corp

  5. Hacking RL 1. Information gathering 2. Scanning 3. Exploitation & privilege escalation 4. Maintaining access & covering tracks

  6. What is RL? , end, info

  7. Our Hobby: Developing FractalAI "Study hard what interests you the most in the most undisciplined, irreverent and original manner possible.” R. P. Feynman Sergio Hernández Guillem Duran @EntropyFarmer @Miau_DB

  8. Causal entropic forces - Paper by Alex. Wissner-Gross (2013) - Intelligence is a thermodynamic process - No neural networks → Equations

  9. Number of future Intelligent decision possible outcomes Direction of maximum Given your current state

  10. Count all the paths that exist Until you reach the time horizon Map them to a score

  11. Cone: Space of future Sample random possible outcomes walks Zero score Present Move away from the wall so fewer walks get 0 score

  14. Nobody likes entropic forces Paper Released - All rewards equal 1 - NP hard!

  15. FractalAI ● Finds low probability points and paths ● Constrained resources ● Total control of exploration process ● Linear time

  16. FractalAI A set of rules for: 1. Defining a cloud of points (Swarm) 2. Moving a Swarm in any Cone 3. Measuring and comparing Swarms 4. Analyzing the history of a Swarm

  17. Hacking RL 1. Information gathering 2. Finding vulnerabilities & Scanning 3. Exploitation & privilege escalation 4. Covering tracks & Maintaining access

  18. RL , end, info

  19. Finding an attack vector

  20. Swarms are cool - They move in linear time . - Pixels/RAM + Reward . - They guess density distributions - They follow useful paths

  22. Cunningham's Law "The best way to get the right answer on FractalAI the Internet is not to ask a question; it's SW FMC to post the wrong answer ."

  23. Using a Swarm to generate data ● S warm W ave (SW) - Move a Swarm → Sample state space - Cone → Tree of visited states - Efficient → Only one tree

  25. Using a Swarm to generate data ● S warm W ave (SW) - Move a Swarm → Sample state space - Cone → Tree of visited states - Efficient → Only one tree ● F ractal M onte C arlo (FMC) - 1 Cone per action - Robust → Stochastic/difficult envs - Distribution of action utility

  26. Hardcore Lunar Lander Fuel HP Rubber band 2 Continuous Hook FIRE DoF

  27. Reward The Gameplay - Health + Fuel level - Closer to target → +0.2 - Reach target → +100 Catch rock outside this circle Bring rock here Don’t crash!

  28. FMC Cone - Grey lines: Rocket Paths Catch Rock Drop Rock - Colored lines: Rock attached Hook’s Path - Colored change: New target (Pick up/drop rock)

  30. Hacking RL 1. Information gathering 2. Scanning 3. Exploitation & privilege escalation 4. Maintaining access & covering tracks

  31. Demo time!

  32. Hacking RL 1. Information gathering 2. Scanning 3. Exploitation & privilege escalation 4. Maintaining access & managing tracks

  33. Performance of the Swarm Wave

  34. Robust to sparse rewards

  35. Solving Atari games is easy

  36. SW is useful in virtually all environments

  37. Fractal Monte Carlo

  40. Control swarms of agents

  41. Multi objective environments

  42. Hacking OpenAI Baselines Run_atary.py → inject hacked env. A2c.py → recover action

  45. Guillem Duran Ballester Guillemdb Let’s coauthor papers or hire me! - PyData Mallorca co organizer - Save tons of money! - SW & FMC are simple - Telecomm. Engineer - My hobby: hacking AI stuff - I learn stuff super fast - RL Researcher Wannabe - I like teaching & sharing

  46. Thank You! Please Hack us: 1. Talk repo: Guillemdb/hacking-rl @Miau_DB 2. Code: FragileTheory/FractalAI @Entropyfarmer 3. More than 100 videos 4. PDFs on arXiv.org

  47. Additional Material ● How the algorithm works ● An overview of the FractalAI repository ● Reinforcement Learning as a supervised problem ● Hacking OpenAI baselines ● Papers that need some love ● Improving AlphaZero ● Combining FractalAI with neural networks

  48. The Algorithm 1. Random perturbation of the walkers 2. Calculate the virtual reward of each walker a. Distance to 1 random walker b. Reward of current state 3. Clone the walkers → Balance the Swarm

  49. Random perturbation

  50. Walkers & Reward density

  51. Cloning Process

  52. Cloning balances both densities

  53. Choose the action that most walkers share

  54. RL is training a DNN model ● ML without labels → Environment ● Sample the environment ● Dataset of games → Map states to scores ● Predict good actions

  55. Which Envs are compromised? ● Atari games → Solved 32 Games! ● Sega games → Good performance ● dm_control → x1000+ with tricks ● I hope soon in DoTA 2 & challenging environments

  56. If you run it on your laptop in 50 games - Pwns planning SoTA - Cheaper than a human (No Pitfall) - 17+ games with max scores (1M Bug) - Beats human record → 56.36% games

  57. RL as a supervised task ● Train autoencoder with a SW ● Generate 1M Games and overfit on them ● Use a GAN to mimic a fractal ● Use FMC to calculate Q-vals/Advantages ● Trained model as a prior

  58. Give love to papers! ● Reproducing world models ● Playing Atari from demonstrations (OpenAI) ● Playing Atari from YouTube Videos (Deepmind) ● RUDDER

  59. Efficiency on MsPacman An example run: SW vs. UCT & p-IW (Assuming 2 x M4.16xlarge) - 128 walkers - 14.20 samples / action UCT 150k p-IW 150k p-IW 0.5s p-IW 32s - Scored 27971 points Score x1.25 x0.91 x1.85 x1.21 - Game len 6892 - 97894 samples Sampling x1260 x1260 x1848 x29581 Efficiency - 1min 38s. Runtime - 70.34 fps When UCT(AlphaZero) finishes ⅔ of its first step, SW has already beaten by 25% its final score

  60. Improving Alphazero ● Change UTC for SW → sample x1000 + faster ● Stones as reward → SW jumps local optima ● Embedding of conv. layers for distance ● Use FMC to get better Q-values ● Heuristics only valid in Go

  61. SW: Presenting an unfair benchmark ● A fair benchmark requires sampling 1M score at 150k samples / step - 10 min play: 12000 steps - One step: 400 µs - 1 core game: 4.8s x 150k x 50 rounds -> 416 days - Ideal M4.16xlarge: $3.20 / Hour → 500$ per game running 1 instance for 6.5 days - 26,500$ on 53 games → Sponsors are welcome

  62. Counting Paths vs. Trees ● Samples / step: confusing → Tree of games Traditional Planning Swarm Wave

Recommend

Deep Reinforcement Learning Applications + Hacking Arjun Chandra Research Scientist Telenor

Deep Reinforcement Learning Applications + Hacking Arjun Chandra Research Scientist Telenor

Deep Reinforcement Learning Applications + Hacking Arjun Chandra Research Scientist Telenor Research / Telenor-NTNU AI Lab arjun.chandra@telenor.com @boelger 21 November 2017 https://join.slack.com/t/deep-rl-tutorial/signup The Plan Few

258 views • 24 slides
RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

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
Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine playing a new game whose rules you dont know; after a hundred or so moves your don t know; after a hundred or so moves, your opponent announces, You

511 views • 30 slides
Reinforcement Learning You can think of supervised learning as the teacher providing answers

Reinforcement Learning You can think of supervised learning as the teacher providing answers

Reinforcement Learning You can think of supervised learning as the teacher providing answers (the class labels) Reinforcement learning: In reinforcement learning, the agent learns Markov Decision Processes based on a punishment/reward

89 views • 6 slides
Examples of Reinforcement Learning Robocup Soccer Teams Stone & Veloso, Reidmiller et al.

Examples of Reinforcement Learning Robocup Soccer Teams Stone & Veloso, Reidmiller et al.

Reinforcement Learning Slides by Rich Sutton Mods by Dan Lizotte Refer to Reinforcement Learning: An Introduction by Sutton and Barto Alpaydin Chapter 16 Up until now we have been Supervised Learning Classifying, mostly

891 views • 31 slides
CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning Haarnoja, Tang et al. (2017) Reinforcement Learning with Deep Energy Based Policies, ICML . Haarnoja, Zhou et al. (2018) Soft Actor-Critic: Off-Policy

682 views • 24 slides
Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control Theory, you actually have some knowledge in RL. RL shares the overall goal with OCT: solving for a control policy such that the cumulative cost

610 views • 22 slides
R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec 03 2008 1 Large State Spaces h When a problem has a large state space we can not longer represent the U or Q functions as explicit tables explicit

436 views • 18 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still assume a Marko kov decision process (MDP): A se set o of st states s s S A se set o of a actions ( s (per st state) A A mo model

96 views • 5 slides
Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning? Spring 2019 Created:

371 views • 15 slides
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.

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
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

540 views • 15 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi Willem van de Meent Northeastern University [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188

145 views • 10 slides
Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning: an Introduction, 2nd Edition: Chapters 6 (6.1 6.5) Outline Reinforcement Learning Reinforcement Learning: the

587 views • 27 slides
Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and Reinforcement Learning University of Waterloo Machine Learning Supervised Learning Teacher tells learner what to remember Reinforcement Learning

401 views • 29 slides
1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

CSE 573: Artificial Intelligence Todo Reinforcement Learning Add simulations from 473 Dan Weld Add UCB bound (cut bolzman & constant epsilon Add snazzy videos (pendulum, zico kolter See http://www See http://www-

462 views • 11 slides
Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest Lecture May 24, 2017 Lecture overview What makes a reinforcement learning algorithm safe ? Notation Creating a safe reinforcement learning

1.42k views • 88 slides
Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

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
Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007 sequential decision making under uncertainty ? How Can I ... ? Move around in the physical world (e.g. driving, navigation) Play and win a game

519 views • 21 slides
Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper

Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper

Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper by Bello, I., Pham, H., Le, Q. V., Norouzi, M., & Bengio, S. (2016) Presented by Yan Shi Outline 1. Introduction 2. Background 3. Algorithms

966 views • 27 slides
Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value

Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value

5/7/2012 CSE 473: Artificial Intelligence Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value iteration Q-learning Exploration / exploitation Linear function approximation Linear function

159 views • 12 slides
CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement Learning Animesh Garg Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning Richard S. Sutton , Doina

2.18k views • 29 slides
Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M.

Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M.

Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M. Soleymani Fall 2018 Most slides have been taken from Klein and Abdeel, CS188, UC Berkeley. Reinforcement Learning (RL) Learning as a result of

1.45k views • 133 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

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

More recommend