Related papers: Combining Evolutionary Search with Behaviour Cloni…
Evolution gave rise to human and animal intelligence here on Earth. We argue that the path to developing artificial human-like-intelligence will pass through mimicking the evolutionary process in a nature-like simulation. In Nature, there…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…
Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is…
In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels. TOAD-GAN follows the SinGAN…
Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…
One of the main problems of evolutionary algorithms is the convergence of the population to local minima. In this paper, we explore techniques that can avoid this problem by encouraging a diverse behavior of the agents through a shared…
Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has become a useful reinforcement learning (RL) framework for…
Evolutionary Learning proceeds by evolving a population of classifiers, from which it generally returns (with some notable exceptions) the single best-of-run classifier as final result. In the meanwhile, Ensemble Learning, one of the most…
Modern day computer games have extremely large state and action spaces. To detect bugs in these games' models, human testers play the games repeatedly to explore the game and find errors in the games. Such gameplay is exhaustive and time…
Policy gradient reinforcement learning (RL) algorithms have achieved impressive performance in challenging learning tasks such as continuous control, but suffer from high sample complexity. Experience replay is a commonly used approach to…
In response to the limitations of reinforcement learning and evolutionary algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. EvoRL integrates EAs and reinforcement…
Machine Learning techniques have been used to teach computer programs how to play games as complicated as Chess and Go. These were achieved using powerful tools such as Neural Networks and Parallel Computing on Supercomputers. In this…
Empathetic response generation, aiming to understand the user's situation and feelings and respond empathically, is crucial in building human-like dialogue systems. Traditional approaches typically employ maximum likelihood estimation as…
We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the…
Previous work explored blending levels from existing games to create levels for a new game that mixes properties of the original games. In this paper, we use Variational Autoencoders (VAEs) for improving upon such techniques. VAEs are…
Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously…
Reasoning over structured graphs remains a fundamental challenge for Large Language Models (LLMs), particularly when scaling to large graphs. Existing approaches typically follow the retrieval-augmented generation (RAG) paradigm: first…
It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames…
Actor-critic deep reinforcement learning (DRL) algorithms have recently achieved prominent success in tackling various challenging reinforcement learning (RL) problems, particularly complex control tasks with high-dimensional continuous…
We consider a pursuit-evasion game [11] played between two agents, 'Blue' (the pursuer) and 'Red' (the evader), over $T$ time steps. Red aims to attack Blue's territory. Blue's objective is to intercept Red by time $T$ and thereby limit the…