相关论文: Diversity Induced Environment Design via Self-Play

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck…

Quality-Diversity optimization is a new family of optimization algorithms that, instead of searching for a single optimal solution to solving a task, searches for a large collection of solutions that all solve the task in a different way.…

Recent works have proven that intricate cooperative behaviors can emerge in agents trained using meta reinforcement learning on open ended task distributions using self-play. While the results are impressive, we argue that self-play and…

Quality diversity (QD) is a branch of evolutionary computation that seeks high-quality and behaviorally diverse solutions to a problem. While adversarial problems are common, classical QD cannot be easily applied to them, as both the…

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a…

Embodied agents struggle to generalize to new environments, even when those environments share similar underlying structures to their training settings. Most current approaches to generating these training environments follow an open-loop…

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse…

Recent studies have highlighted the interplay between diffusion models and representation learning. Intermediate representations from diffusion models can be leveraged for downstream visual tasks, while self-supervised vision models can…

Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. RL is also very brittle; agents often overfit to their training…

A fascinating aspect of nature lies in its ability to produce a large and diverse collection of organisms that are all high-performing in their niche. By contrast, most AI algorithms focus on finding a single efficient solution to a given…

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex…

Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout…

Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected…

Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic"…

Evolutionary science provides evidence that diversity confers resilience in natural systems. Yet, traditional multi-agent reinforcement learning techniques commonly enforce homogeneity to increase training sample efficiency. When a system…

Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of diverse skills that provide a thorough coverage of the state…

Results from a triple-blind mixed-method user study into the effectiveness of mixed-initiative tools for the procedural generation of game levels are presented. A tool which generates levels using interactive evolutionary optimisation was…