Related papers: Combining Tree-Search, Generative Models, and Nash…
Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable…
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the…
The combination of Monte-Carlo Tree Search (MCTS) and deep reinforcement learning is state-of-the-art in two-player perfect-information games. In this paper, we describe a search algorithm that uses a variant of MCTS which we enhanced by 1)…
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GAN is essentially a two-player zero-sum game between the…
Scalable multi-agent reinforcement learning (MARL) remains a central challenge for AI. Existing population-based methods, like Policy-Space Response Oracles, PSRO, require storing explicit policy populations and constructing full payoff…
Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL) technique that iteratively applies MCTS on batches of…
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal…
Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on…
While many recent advances in deep reinforcement learning (RL) rely on model-free methods, model-based approaches remain an alluring prospect for their potential to exploit unsupervised data to learn environment model. In this work, we…
Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness. A key difficulty of such approach lies in making accurate predictions about the decisions of other…
Well-trained multi-agent systems can fail when deployed in real-world environments due to model mismatches between the training and deployment environments, caused by environment uncertainties including noise or adversarial attacks.…
The goal of agents in multi-agent environments is to maximize total reward against the opposing agents that are encountered. Following a game-theoretic solution concept, such as Nash equilibrium, may obtain a strong performance in some…
Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a `local Nash equilibrium` (LNE). Such LNEs, however, can be arbitrarily far from an actual Nash…
Researchers have demonstrated that neural networks are vulnerable to adversarial examples and subtle environment changes, both of which one can view as a form of distribution shift. To humans, the resulting errors can look like blunders,…
Negotiation is a process where agents aim to work through disputes and maximize their surplus. As the use of deep reinforcement learning in bargaining games is unexplored, this paper evaluates its ability to exploit, adapt, and cooperate to…
The Generative Adversarial Network (GAN) was recently introduced in the literature as a novel machine learning method for training generative models. It has many applications in statistics such as nonparametric clustering and nonparametric…
Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash)…
To achieve a high learning accuracy, generative adversarial networks (GANs) must be fed by large datasets that adequately represent the data space. However, in many scenarios, the available datasets may be limited and distributed across…
Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolution strategies) help…
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by…