The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-Agent Challenge (SMAC) has become a popular testbed for centralised training with decentralised execution. However, after years of sustained improvement on SMAC, algorithms now achieve near-perfect performance. In this work, we conduct new analysis demonstrating that SMAC is not sufficiently stochastic to require complex closed-loop policies. In particular, we show that an open-loop policy conditioned only on the timestep can achieve non-trivial win rates for many SMAC scenarios. To address this limitation, we introduce SMACv2, a new version of the benchmark where scenarios are procedurally generated and require agents to generalise to previously unseen settings (from the same distribution) during evaluation. We show that these changes ensure the benchmark requires the use of closed-loop policies. We evaluate state-of-the-art algorithms on SMACv2 and show that it presents significant challenges not present in the original benchmark. Our analysis illustrates that SMACv2 addresses the discovered deficiencies of SMAC and can help benchmark the next generation of MARL methods. Videos of training are available at https://sites.google.com/view/smacv2
Multiagent learning settings are inherently more difficult than single-agent learning because each agent interacts with other simultaneously learning agents in a shared environment. An effective approach in multiagent reinforcement learning is to consider the learning process of agents and influence their future policies toward desirable behaviors from each agent's perspective. Importantly, if each agent maximizes its long-term rewards by accounting for the impact of its behavior on the set of convergence policies, the resulting multiagent system reaches an active equilibrium. While this new solution concept is general such that standard solution concepts, such as a Nash equilibrium, are special cases of active equilibria, it is unclear when an active equilibrium is a preferred equilibrium over other solution concepts. In this paper, we analyze active equilibria from a game-theoretic perspective by closely studying examples where Nash equilibria are known. By directly comparing active equilibria to Nash equilibria in these examples, we find that active equilibria find more effective solutions than Nash equilibria, concluding that an active equilibrium is the desired solution for multiagent learning settings.
We introduce a novel machine learning optimizer called LODO, which online meta-learns an implicit inverse Hessian of the loss as a subroutine of quasi-Newton optimization. Our optimizer merges Learning to Optimize (L2O) techniques with quasi-Newton methods to learn neural representations of symmetric matrix vector products, which are more flexible than those in other quasi-Newton methods. Unlike other L2O methods, ours does not require any meta-training on a training task distribution, and instead learns to optimize on the fly while optimizing on the test task, adapting to the local characteristics of the loss landscape while traversing it. Theoretically, we show that our optimizer approximates the inverse Hessian in noisy loss landscapes and is capable of representing a wide range of inverse Hessians. We experimentally verify our algorithm's performance in the presence of noise, and show that simpler alternatives for representing the inverse Hessians worsen performance. Lastly, we use our optimizer to train a semi-realistic deep neural network with 95k parameters, and obtain competitive results against standard neural network optimizers.
Autonomous intelligent agents deployed to the real-world need to be robust against adversarial attacks on sensory inputs. Existing work in reinforcement learning focuses on minimum-norm perturbation attacks, which were originally introduced to mimic a notion of perceptual invariance in computer vision. In this paper, we note that such minimum-norm perturbation attacks can be trivially detected by victim agents, as these result in observation sequences that are not consistent with the victim agent's actions. Furthermore, many real-world agents, such as physical robots, commonly operate under human supervisors, which are not susceptible to such perturbation attacks. As a result, we propose to instead focus on illusionary attacks, a novel form of attack that is consistent with the world model of the victim agent. We provide a formal definition of this novel attack framework, explore its characteristics under a variety of conditions, and conclude that agents must seek realism feedback to be robust to illusionary attacks.
The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by Hu et al. 2020 as the zero-shot coordination (ZSC) setting and partially addressed with their Other-Play (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually incompatible way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) Costa Gomes et al. 2006, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.
The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward dynamics. An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other interacting agents and influence the evolution of their future policies towards desirable behavior for its own benefit. Unfortunately, all previous approaches for achieving this suffer from myopic evaluation, considering only a few or a finite number of updates to the policies of other agents. In this paper, we propose a principled framework for considering the limiting policies of other agents as the time approaches infinity. Specifically, we develop a new optimization objective that maximizes each agent's average reward by directly accounting for the impact of its behavior on the limiting set of policies that other agents will take on. Thanks to our farsighted evaluation, we demonstrate better long-term performance than state-of-the-art baselines in various domains, including the full spectrum of general-sum, competitive, and cooperative settings.
Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization. However, these algorithms may require careful hyperparameter tuning for each problem instance. We use a reinforcement learning agent in conjunction with a quantum-inspired algorithm to solve the Ising energy minimization problem, which is equivalent to the Maximum Cut problem. The agent controls the algorithm by tuning one of its parameters with the goal of improving recently seen solutions. We propose a new Rescaled Ranked Reward (R3) method that enables stable single-player version of self-play training that helps the agent to escape local optima. The training on any problem instance can be accelerated by applying transfer learning from an agent trained on randomly generated problems. Our approach allows sampling high-quality solutions to the Ising problem with high probability and outperforms both baseline heuristics and a black-box hyperparameter optimization approach.
Producing agents that can generalize to a wide range of environments is a significant challenge in reinforcement learning. One method for overcoming this issue is domain randomization, whereby at the start of each training episode some parameters of the environment are randomized so that the agent is exposed to many possible variations. However, domain randomization is highly inefficient and may lead to policies with high variance across domains. In this work, we formalize the domain randomization problem, and show that minimizing the policy's Lipschitz constant with respect to the randomization parameters leads to low variance in the learned policies. We propose a method where the agent only needs to be trained on one variation of the environment, and its learned state representations are regularized during training to minimize this constant. We conduct experiments that demonstrate that our technique leads to more efficient and robust learning than standard domain randomization, while achieving equal generalization scores.
Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary given the complexity of the optimization task. We instead propose that the agent should seek to continuously improve the solution by learning to explore at test time. Our approach of exploratory combinatorial optimization (ECO-DQN) is, in principle, applicable to any combinatorial problem that can be defined on a graph. Experimentally, we show our method to produce state-of-the-art RL performance on the Maximum Cut problem. Moreover, because ECO-DQN can start from any arbitrary configuration, it can be combined with other search methods to further improve performance, which we demonstrate using a simple random search.