Efficient Competitive Self-Play Policy Optimization

• URL: http://arxiv.org/abs/2009.06086v1
• Date: Sun, 13 Sep 2020 21:01:38 GMT
• Title: Efficient Competitive Self-Play Policy Optimization
• Authors: Yuanyi Zhong, Yuan Zhou, Jian Peng
• Abstract summary: We propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games. Our method trains several agents simultaneously, and intelligently takes each other as opponent based on simple adversarial rules. We prove theoretically that our algorithm converges to an approximate equilibrium with high probability in convex-concave games.
• Score: 20.023522000925094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement. In previous work, heuristic rules are designed to choose an opponent for the current learner. Typical rules include choosing the latest agent, the best agent, or a random historical agent. However, these rules may be inefficient in practice and sometimes do not guarantee convergence even in the simplest matrix games. In this paper, we propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games. We recognize the fact that the Nash equilibrium coincides with the saddle point of the stochastic payoff function, which motivates us to borrow ideas from classical saddle point optimization literature. Our method trains several agents simultaneously, and intelligently takes each other as opponent based on simple adversarial rules derived from a principled perturbation-based saddle optimization method. We prove theoretically that our algorithm converges to an approximate equilibrium with high probability in convex-concave games under standard assumptions. Beyond the theory, we further show the empirical superiority of our method over baseline methods relying on the aforementioned opponent-selection heuristics in matrix games, grid-world soccer, Gomoku, and simulated robot sumo, with neural net policy function approximators.

Related papers

• A Minimaximalist Approach to Reinforcement Learning from Human Feedback [49.45285664482369]
  We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches.
  arXiv  Detail & Related papers  (2024-01-08T17:55:02Z)
• Offline Learning in Markov Games with General Function Approximation [22.2472618685325]
  We study offline multi-agent reinforcement learning (RL) in Markov games. We provide the first framework for sample-efficient offline learning in Markov games.
  arXiv  Detail & Related papers  (2023-02-06T05:22:27Z)
• Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks [83.28949556413717]
  We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. We model players' strategies using artificial neural networks. This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
  arXiv  Detail & Related papers  (2022-11-29T05:16:41Z)
• Efficiently Computing Nash Equilibria in Adversarial Team Markov Games [19.717850955051837]
  We introduce a class of games in which a team identically players is competing against an adversarial player. This setting allows for a unifying treatment of zero-sum Markov games potential games. Our main contribution is the first algorithm for computing stationary $epsilon$-approximate Nash equilibria in adversarial team Markov games.
  arXiv  Detail & Related papers  (2022-08-03T16:41:01Z)
• Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions [145.54544979467872]
  We propose and analyze new fictitious play policy optimization algorithms for zero-sum Markov games with structured but unknown transitions. We prove tight $widetildemathcalO(sqrtK)$ regret bounds after $K$ episodes in a two-agent competitive game scenario. Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization.
  arXiv  Detail & Related papers  (2022-07-25T18:29:16Z)
• Towards convergence to Nash equilibria in two-team zero-sum games [17.4461045395989]
  Two-team zero-sum games are defined as multi-player games where players are split into two competing sets of agents. We focus on the solution concept of Nash equilibria (NE) We show that computing NE for this class of games is $textithard$ for the complexity class $mathrm$.
  arXiv  Detail & Related papers  (2021-11-07T21:15:35Z)
• Provable Fictitious Play for General Mean-Field Games [111.44976345867005]
  We propose a reinforcement learning algorithm for stationary mean-field games. The goal is to learn a pair of mean-field state and stationary policy that constitutes the Nash equilibrium.
  arXiv  Detail & Related papers  (2020-10-08T18:46:48Z)
• Learning to Play Sequential Games versus Unknown Opponents [93.8672371143881]
  We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents. Our results include algorithm's regret guarantees that depend on the regularity of the opponent's response.
  arXiv  Detail & Related papers  (2020-07-10T09:33:05Z)
• Provable Self-Play Algorithms for Competitive Reinforcement Learning [48.12602400021397]
  We study self-play in competitive reinforcement learning under the setting of Markov games. We show that a self-play algorithm achieves regret $tildemathcalO(sqrtT)$ after playing $T$ steps of the game. We also introduce an explore-then-exploit style algorithm, which achieves a slightly worse regret $tildemathcalO(T2/3)$, but is guaranteed to run in time even in the worst case.
  arXiv  Detail & Related papers  (2020-02-10T18:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.