Jakob Foerster

is this you? claim profile

0 followers

  • Stable Opponent Shaping in Differentiable Games

    A growing number of learning methods are actually games which optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to improve learning dynamics in such games, accounting for the fact that the 'environment' includes agents adapting to one another's updates. Learning with Opponent-Learning Awareness (LOLA) is a recent algorithm which exploits this dynamic response and encourages cooperation in settings like the Iterated Prisoner's Dilemma. Although experimentally successful, we show that LOLA can exhibit 'arrogant' behaviour directly at odds with convergence. In fact, remarkably few algorithms have theoretical guarantees applying across all differentiable games. In this paper we present Stable Opponent Shaping (SOS), a new method that interpolates between LOLA and a stable variant named LookAhead. We prove that LookAhead locally converges and avoids strict saddles in all differentiable games, the strongest results in the field so far. SOS inherits these desirable guarantees, while also shaping the learning of opponents and consistently either matching or outperforming LOLA experimentally.

    11/20/2018 ∙ by Alistair Letcher, et al. ∙ 74 share

    read it

  • A Survey of Reinforcement Learning Informed by Natural Language

    To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.

    06/10/2019 ∙ by Jelena Luketina, et al. ∙ 52 share

    read it

  • The StarCraft Multi-Agent Challenge

    In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

    02/11/2019 ∙ by Mikayel Samvelyan, et al. ∙ 32 share

    read it

  • On the Pitfalls of Measuring Emergent Communication

    How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication abilities. As we move towards more complex environments, it becomes imperative to have a set of finer tools that allow qualitative and quantitative insights into the emergence of communication. This may be especially useful to allow humans to monitor agents' behaviour, whether for fault detection, assessing performance, or even building trust. In this paper, we examine a few intuitive existing metrics for measuring communication, and show that they can be misleading. Specifically, by training deep reinforcement learning agents to play simple matrix games augmented with a communication channel, we find a scenario where agents appear to communicate (their messages provide information about their subsequent action), and yet the messages do not impact the environment or other agent in any way. We explain this phenomenon using ablation studies and by visualizing the representations of the learned policies. We also survey some commonly used metrics for measuring emergent communication, and provide recommendations as to when these metrics should be used.

    03/12/2019 ∙ by Ryan Lowe, et al. ∙ 14 share

    read it

  • Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

    Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on single-agent RL to the multi-agent setting. A major stumbling block is that independent Q-learning, the most popular multi-agent RL method, introduces nonstationarity that makes it incompatible with the experience replay memory on which deep Q-learning relies. This paper proposes two methods that address this problem: 1) using a multi-agent variant of importance sampling to naturally decay obsolete data and 2) conditioning each agent's value function on a fingerprint that disambiguates the age of the data sampled from the replay memory. Results on a challenging decentralised variant of StarCraft unit micromanagement confirm that these methods enable the successful combination of experience replay with multi-agent RL.

    02/28/2017 ∙ by Jakob Foerster, et al. ∙ 0 share

    read it

  • Counterfactual Multi-Agent Policy Gradients

    Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent's action, while keeping the other agents' actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actor-critic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

    05/24/2017 ∙ by Jakob Foerster, et al. ∙ 0 share

    read it

  • DiCE: The Infinitely Differentiable Monte-Carlo Estimator

    The score function estimator is widely used for estimating gradients of stochastic objectives in Stochastic Computation Graphs (SCG), eg. in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by differentiating a surrogate loss (SL) objective is computationally and conceptually simple, using the same approach for higher-order gradients is more challenging. Firstly, analytically deriving and implementing such estimators is laborious and not compliant with automatic differentiation. Secondly, repeatedly applying SL to construct new objectives for each order gradient involves increasingly cumbersome graph manipulations. Lastly, to match the first-order gradient under differentiation, SL treats part of the cost as a fixed sample, which we show leads to missing and wrong terms for higher-order gradient estimators. To address all these shortcomings in a unified way, we introduce DiCE, which provides a single objective that can be differentiated repeatedly, generating correct gradient estimators of any order in SCGs. Unlike SL, DiCE relies on automatic differentiation for performing the requisite graph manipulations. We verify the correctness of DiCE both through a proof and through numerical evaluation of the DiCE gradient estimates. We also use DiCE to propose and evaluate a novel approach for multi-agent learning. Our code is available at https://goo.gl/xkkGxN.

    02/14/2018 ∙ by Jakob Foerster, et al. ∙ 0 share

    read it

  • Fake News in Social Networks

    We model the spread of news as a social learning game on a network. Agents can either endorse or oppose a claim made in a piece of news, which itself may be either true or false. Agents base their decision on a private signal and their neighbors' past actions. Given these inputs, agents follow strategies derived via multi-agent deep reinforcement learning and receive utility from acting in accordance with the veracity of claims. Our framework yields strategies with agent utility close to a theoretical, Bayes optimal benchmark, while remaining flexible to model re-specification. Optimized strategies allow agents to correctly identify most false claims, when all agents receive unbiased private signals. However, an adversary's attempt to spread fake news by targeting a subset of agents with a biased private signal can be successful. Even more so when the adversary has information about agents' network position or private signal. When agents are aware of the presence of an adversary they re-optimize their strategies in the training stage and the adversary's attack is less effective. Hence, exposing agents to the possibility of fake news can be an effective way to curtail the spread of fake news in social networks. Our results also highlight that information about the users' private beliefs and their social network structure can be extremely valuable to adversaries and should be well protected.

    08/21/2017 ∙ by Christoph Aymanns, et al. ∙ 0 share

    read it

  • QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

    In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods.

    03/30/2018 ∙ by Tabish Rashid, et al. ∙ 0 share

    read it

  • The Mechanics of n-Player Differentiable Games

    The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, where there are multiple interacting losses. The behavior of gradient-based methods in games is not well understood -- and is becoming increasingly important as adversarial and multi-objective architectures proliferate. In this paper, we develop new techniques to understand and control the dynamics in general games. The key result is to decompose the second-order dynamics into two components. The first is related to potential games, which reduce to gradient descent on an implicit function; the second relates to Hamiltonian games, a new class of games that obey a conservation law, akin to conservation laws in classical mechanical systems. The decomposition motivates Symplectic Gradient Adjustment (SGA), a new algorithm for finding stable fixed points in general games. Basic experiments show SGA is competitive with recently proposed algorithms for finding local Nash equilibria in GANs -- whilst at the same time being applicable to -- and having guarantees in -- much more general games.

    02/15/2018 ∙ by David Balduzzi, et al. ∙ 0 share

    read it

  • Pommerman: A Multi-Agent Playground

    We present Pommerman, a multi-agent environment based on the classic console game Bomberman. Pommerman consists of a set of scenarios, each having at least four players and containing both cooperative and competitive aspects. We believe that success in Pommerman will require a diverse set of tools and methods, including planning, opponent/teammate modeling, game theory, and communication, and consequently can serve well as a multi-agent benchmark. To date, we have already hosted one competition, and our next one will be featured in the NIPS 2018 competition track.

    09/19/2018 ∙ by Cinjon Resnick, et al. ∙ 0 share

    read it