Related papers: Phasic Diversity Optimization for Population-Based…

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…

Policy gradients-based reinforcement learning has proven to be a promising approach for directly optimizing non-differentiable evaluation metrics for language generation tasks. However, optimizing for a specific metric reward leads to…

Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent to maximize expected win-rates against its current or…

Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or…

In Reinforcement Learning (RL), multi-armed Bandit (MAB) problems have found applications across diverse domains such as recommender systems, healthcare, and finance. Traditional MAB algorithms typically assume stationary reward…

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic…

Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that…

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Optimization problems find widespread use in both single-objective and multi-objective scenarios. In practical applications, users aspire for solutions that converge to the region of interest (ROI) along the Pareto front (PF). While the…

Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimization (HPO) algorithms have been developed to address this…

Conventional Multi-Armed Bandit (MAB) algorithms are designed for stationary environments, where the reward distributions associated with the arms do not change with time. In many applications, however, the environment is more accurately…

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel…

Generating various strategies for a given task is challenging. However, it has already proven to bring many assets to the main learning process, such as improved behavior exploration. With the growth in the interest of heterogeneity in…

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Motivated by applications such as online labor markets we consider a variant of the stochastic multi-armed bandit problem where we have a collection of arms representing strategic agents with different performance characteristics. The…

The tuning of hyperparameters in reinforcement learning (RL) is critical, as these parameters significantly impact an agent's performance and learning efficiency. Dynamic adjustment of hyperparameters during the training process can…