No abstract

Efficient exploration is important for reinforcement learners (RL) to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a new general framework for improving coordination and performance of multi-agent reinforcement learners (MARL). Our framework, named Learnable Intrinsic-Reward Generation Selection algorithm (LIGS) introduces an adaptive learner, Generator that observes the agents and learns to construct intrinsic rewards online that coordinate the agents' joint exploration and joint behaviour. Using a novel combination of reinforcement learning (RL) and switching controls, LIGS determines the best states to learn to add intrinsic rewards which leads to a highly efficient learning process. LIGS can subdivide complex tasks making them easier to solve and enables systems of RL agents to quickly solve environments with sparse rewards. LIGS can seamlessly adopt existing multi-agent RL algorithms and our theory shows that it ensures convergence to joint policies that deliver higher system performance. We demonstrate the superior performance of the LIGS framework in challenging tasks in Foraging and StarCraft II. To aid coordinated learning, algorithms such as QMIX Rashid et al. (2018), MAVEN Mahajan et al. (2019) and COMA Foerster et al. (2018), so-called centralised critic and decentralised execution (CT-DE) methods use a centralised critic whose role is to estimate the agents' expected returns. The critic * Correspondence to

In this paper, we shed new light on the generalization ability of deep learningbased solvers for Traveling Salesman Problems (TSP). Specifically, we introduce a two-player zero-sum framework between a trainable Solver and a Data Generator, where the Solver aims to solve the task instances provided by the Generator, and the Generator aims to generate increasingly difficult instances for improving the Solver. Grounded in Policy Space Response Oracle (PSRO) methods, our two-player framework outputs a population of best-responding Solvers, over which we can mix and output a combined model that achieves the least exploitability against the Generator, and thereby the most generalizable performance on different TSP tasks. We conduct experiments on a variety of TSP instances with different types and sizes. Results suggest that our Solvers achieve the state-of-the-art performance even on tasks the Solver never meets, whilst the performance of other deep learning-based Solvers drops sharply due to over-fitting. On real-world instances from TSPLIB, our method also attains a 12% improvement, in terms of optimal gap, over the best baseline model. To demonstrate the principle of our framework, we study the learning outcome of the proposed two-player game and demonstrate that the exploitability of the Solver population decreases during training, and it eventually approximates the Nash equilibrium along with the Generator.

No abstract

Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to realworld domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that behavioural diversity is a pivotal, yet under-explored, component for real-world multiagent learning systems, and that significant work remains in understanding how to design a diversity-aware auto-curriculum. We list four open challenges for auto-curriculum techniques, which we believe deserve more attention from this community. Towards validating our vision, we recommend modelling realistic interactive behaviours in autonomous driving as an important test bed, and recommend the SMARTS/ULTRA benchmark.