๐Ÿ˜‡
Deep Multi-Agent Reinforcement Learning
  • Deep Multi-Agent Reinforcement Learning
  • Abstract & Contents
    • Abstract
  • 1. Introduction
    • 1. INTRODUCTION
      • 1.1 The Industrial Revolution, Cognition, and Computers
      • 1.2 Deep Multi-Agent Reinforcement-Learning
      • 1.3 Overall Structure
  • 2. Background
    • 2. BACKGROUND
      • 2.1 Reinforcement Learning
      • 2.2 Multi-Agent Settings
      • 2.3 Centralized vs Decentralized Control
      • 2.4 Cooperative, Zero-sum, and General-Sum
      • 2.5 Partial Observability
      • 2.6 Centralized Training, Decentralized Execution
      • 2.7 Value Functions
      • 2.8 Nash Equilibria
      • 2.9 Deep Learning for MARL
      • 2.10 Q-Learning and DQN
      • 2.11 Reinforce and Actor-Critic
  • I Learning to Collaborate
    • 3. Counterfactual Multi-Agent Policy Gradients
      • 3.1 Introduction
      • 3.2 Related Work
      • 3.3 Multi-Agent StarCraft Micromanagement
      • 3.4 Methods
        • 3.4.1 Independent Actor-Critic
        • 3.4.2 Counterfactual Multi-Agent Policy Gradients
        • 3.4.2.1 baseline lemma
        • 3.4.2.2 COMA Algorithm
      • 3.5 Results
      • 3.6 Conclusions & Future Work
    • 4 Multi-Agent Common Knowledge Reinforcement Learning
      • 4.1 Introduction
      • 4.2 Related Work
      • 4.3 Dec-POMDP and Features
      • 4.4 Common Knowledge
      • 4.5 Multi-Agent Common Knowledge Reinforcement Learning
      • 4.6 Pairwise MACKRL
      • 4.7 Experiments and Results
      • 4.8 Conclusion & Future Work
    • 5 Stabilizing Experience Replay
      • 5.1 Introduction
      • 5.2 Related Work
      • 5.3 Methods
        • 5.3.1 Multi-Agent Importance Sampling
        • 5.3.2 Multi-Agent Fingerprints
      • 5.4 Experiments
        • 5.4.1 Architecture
      • 5.5 Results
        • 5.5.1 Importance Sampling
        • 5.5.2 Fingerprints
        • 5.5.3 Informative Trajectories
      • 5.6 Conclusion & Future Work
  • II Learning to Communicate
    • 6. Learning to Communicate with Deep Multi-Agent ReinforcementLearning
      • 6.1 Introduction
      • 6.2 Related Work
      • 6.3 Setting
      • 6.4 Methods
        • 6.4.1 Reinforced Inter-Agent Learning
        • 6.4.2 Differentiable Inter-Agent Learning
      • 6.5 DIAL Details
      • 6.6 Experiments
        • 6.6.1 Model Architecture
        • 6.6.2 Switch Riddle
        • 6.6.3 MNIST Games
        • 6.6.4 Effect of Channel Noise
      • 6.7 Conclusion & Future Work
    • 7. Bayesian Action Decoder
      • 7.1 Introduction
      • 7.2 Setting
      • 7.3 Method
        • 7.3.1 Public belief
        • 7.3.2 Public Belief MDP
        • 7.3.3 Sampling Deterministic Partial Policies
        • 7.3.4 Factorized Belief Updates
        • 7.3.5 Self-Consistent Beliefs
      • 7.4 Experiments and Results
        • 7.4.1 Matrix Game
        • 7.4.2 Hanabi
        • 7.4.3 Observations and Actions
        • 7.4.4 Beliefs in Hanabi
        • 7.4.5 Architecture Details for Baselines and Method
        • 7.4.6 Hyperparamters
        • 7.4.7 Results on Hanabi
      • 7.5 Related Work
        • 7.5.1 Learning to Communicate
        • 7.5.2 Research on Hanabi
        • 7.5.3 Belief State Methods
      • 7.6 Conclusion & Future Work
  • III Learning to Reciprocate
    • 8. Learning with Opponent-Learning Awareness
      • 8.1 Introduction
      • 8.2 Related Work
      • 8.3 Methods
        • 8.3.1 Naive Learner
        • 8.3.2 Learning with Opponent Learning Awareness
        • 8.3.3. Learning via Policy gradient
        • 8.3.4 LOLA with Opponent modeling
        • 8.3.5 Higher-Order LOLA
      • 8.4 Experimental Setup
        • 8.4.1 Iterated Games
        • 8.4.2 Coin Game
        • 8.4.3 Training Details
      • 8.5 Results
        • 8.5.1 Iterated Games
        • 8.5.2 Coin Game
        • 8.5.3 Exploitability of LOLA
      • 8.6 Conclusion & Future Work
    • 9. DiCE: The Infinitely Differentiable Monte Carlo Estimator
      • 9.1 Introduction
      • 9.2 Background
        • 9.2.1 Stochastic Computation Graphs
        • 9.2.2 Surrogate Losses
      • 9.3 Higher Order Gradients
        • 9.3.1 Higher Order Gradient Estimators
        • 9.3.2 Higher Order Surrogate Losses
        • 9.3.3. Simple Failing Example
      • 9.4 Correct Gradient Estimators with DiCE
        • 9.4.1 Implement of DiCE
        • 9.4.2 Casuality
        • 9.4.3 First Order Variance Reduction
        • 9.4.4 Hessian-Vector Product
      • 9.5 Case Studies
        • 9.5.1 Empirical Verification
        • 9.5.2 DiCE For multi-agent RL
      • 9.6 Related Work
      • 9.7 Conclusion & Future Work
  • Reference
    • Reference
  • After
    • ๋ณด์ถฉ
    • ์—ญ์ž ํ›„๊ธฐ
Powered by GitBook
On this page

Was this helpful?

  1. III Learning to Reciprocate
  2. 8. Learning with Opponent-Learning Awareness

8.6 Conclusion & Future Work

์ด๋ฒˆ section์—์„œ๋Š” Opponent-Learning Awareness(LOLA)์— ๋Œ€ํ•ด ์•Œ์•„ ๋ณด์•˜์Šต๋‹ˆ๋‹ค. ์ด๋Š” MARL์ƒํ™ฉ์—์„œ ๋‹ค๋ฅธ agent์˜ ํ•™์Šต์„ ๊ณ ๋ คํ•ด ์ž์‹ ์˜ ํ•™์Šต์„ ํ•˜๋Š” ๋ฐฉ๋ฒ•์ž…๋‹ˆ๋‹ค. ์—ฌ๊ธฐ์„œ๋Š” value function์— ๋Œ€ํ•ด ์ ‘๊ทผํ•  ์ˆ˜ ์žˆ์„ ๋•Œ IPD์—์„œ NL์€ defact ์ „๋žต์— ์ˆ˜๋ ดํ•˜๋Š” ๊ฒฝํ–ฅ์„ ๋ณด์˜€์ง€๋งŒ LOLA๋Š” tit-for-tat ์ „๋žต์ด ์šฐ์œ„๋ฅผ ์ ํ•˜๋Š” ๊ฒƒ์„ ๋ณด์•˜์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ, LOLA๊ฐ€ IMP์—์„œ๋„ ๋‚ด์‰ฌ ๊ท ํ˜•์„ ์ด๋ฃจ๋Š” ๊ฒƒ์„ ๋ณด์•˜์Šต๋‹ˆ๋‹ค. ๋‹ค๋ฅธ multi-agent learning algorithm๊ณผ๋„ IPD์™€ IMP์—์„œ ์‹คํ—˜์ ์œผ๋กœ ์ข‹์€ ๊ฒฐ๊ณผ๋ฅผ ๋ณด์ด๋Š” ๊ฒƒ์„ ํ™•์ธํ–ˆ์Šต๋‹ˆ๋‹ค.

value function์— ์ง์ ‘ ์ ‘๊ทผํ•˜์ง€ ๋ชปํ•  ๋•Œ์— ๋Œ€ํ•ด gradient-based version LOLA๋ฅผ ์†Œ๊ฐœํ•˜๊ณ , Coin Game์—์„œ ์ด์˜ ํ•™์Šต์„ ๋ณด์ž…๋‹ˆ๋‹ค. ์ด ๋•Œ, recurrent layer๊ฐ€ ํ•„์š”ํ•จ์„ ๋ณด์•˜๊ณ , LOLA๋Š” coordinationํ•˜๋Š” ๊ฒฝํ–ฅ์„ ๋„๋Š” ๊ฒƒ์„ ๋ณด์•˜์Šต๋‹ˆ๋‹ค. ์ด๋•Œ, opponent์˜ parameter ์ •๋ณด๊ฐ€ ์—†์–ด๋„ ์ด๋ฅผ ์–ด๋А์ •๋„ ํ•ด๊ฒฐํ•  ๋ฐฉ๋ฒ•์— ๋Œ€ํ•ด ์„ค๋ช…ํ–ˆ๊ณ , LOLA์˜ high-order approximation์— ๋Œ€ํ•ด ๋ณด์•˜์Šต๋‹ˆ๋‹ค. ์ด๋Š” IPD์—์„œ agent ๋ชจ๋‘ LOLA๋ฅผ ์‚ฌ์šฉํ•˜๋Š” ๊ฒƒ์ด ์ข‹์€ ์„ฑ๋Šฅ์„ ๋ณด์˜€๊ณ  high order approximation๋กœ ์–ป๋Š” ์ถ”๊ฐ€์ ์ธ ์†Œ๋“์€ ์—†์—ˆ์Šต๋‹ˆ๋‹ค.

์ €์ž๋Š” ์ดํ›„ future work๋กœ ์ ๋Œ€์ ์ธ agent๊ฐ€ gradient-based method๊ฐ€ ์•„๋‹Œ, global search method๋ฅผ ํ†ตํ•ด LOLA๋ฅผ ์ด์šฉํ•˜๋ ค ๋“ค ๋•Œ์— ์–ด๋–ป๊ฒŒ LOLA์˜ ์ทจ์•ฝ์ ์„ ํ•ด๊ฒฐํ•  ์ˆ˜ ์žˆ์„์ง€์— ๋Œ€ํ•ด ํ•ด๊ฒฐํ•˜๋Š” ๊ฒƒ์„ ์—ฐ๊ตฌํ•˜๊ฒ ๋‹ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. LOLA๊ฐ€ naive learner๋ฅผ ์ด์šฉํ•˜๋Š” ๋ฐฉ๋ฒ•์ธ ๋งŒํผ LOLA learner๋ฅผ ์ด์šฉํ•  ์ˆ˜๋‹จ์ด ์žˆ์„ ๊ฒƒ์ด ํƒ€๋‹น์„ฑ ์žˆ๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.

Previous8.5.3 Exploitability of LOLANext9. DiCE: The Infinitely Differentiable Monte Carlo Estimator

Last updated 4 years ago

Was this helpful?