Related papers: Playing Atari Space Invaders with Sparse Cosine Op…

Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are…

Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy…

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement…

In this work we introduce an evolutionary strategy to solve combinatorial optimization tasks, i.e. problems characterized by a discrete search space. In particular, we focus on the Traveling Salesman Problem (TSP), i.e. a famous problem…

The sparse Mixture-of-Experts (Sparse-MoE) framework efficiently scales up model capacity in various domains, such as natural language processing and vision. Sparse-MoEs select a subset of the "experts" (thus, only a portion of the overall…

The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear attention variants mitigate these efficiency constraints by…

Reinforcement learning (RL) has made significant strides in various complex domains. However, identifying an effective policy via RL often necessitates extensive exploration. Imitation learning aims to mitigate this issue by using expert…

We rethink test-time scaling laws from a practical efficiency perspective, revealing that the effectiveness of smaller models is significantly overestimated. Prior work, grounded in compute-optimality, overlooks critical memory access…

Evolutionary computing (EC) is widely used in dealing with combinatorial optimization problems (COP). Traditional EC methods can only solve a single task in a single run, while real-life scenarios often need to solve multiple COPs…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Reinforcement learning is a widely used approach to autonomous navigation, showing potential in various tasks and robotic setups. Still, it often struggles to reach distant goals when safety constraints are imposed (e.g., the wheeled robot…

Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or…

We study evolutionary games in a spatial diluted grid environment in which agents strategically interact locally but can also opportunistically move to other positions within a given migration radius. Using the imitation of the best rule…

Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using…

Formulating expert policies as macro actions promises to alleviate the long-horizon issue via structured exploration and efficient credit assignment. However, traditional option-based multi-policy transfer methods suffer from inefficient…

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity,…

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.…

We investigate an evolutionary multi-objective approach to good micro for real-time strategy games. Good micro helps a player win skirmishes and is one of the keys to developing better real-time strategy game play. In prior work, the same…

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…