Related papers: Genetic Drift Regularization: on preventing Actor …
We study a genetic regulatory network model developed to demonstrate that genetic robustness can evolve through stabilizing selection for optimal phenotypes. We report preliminary results on whether such selection could result in a…
Despite overparameterization, deep networks trained via supervised learning are easy to optimize and exhibit excellent generalization. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit…
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving…
We propose a new method for training an agent via an evolutionary strategy (ES), in which we iteratively improve a set of samples to imitate: Starting with a random set, in every iteration we replace a subset of the samples with samples…
The performance of deep neural networks, such as Deep Belief Networks formed by Restricted Boltzmann Machines (RBMs), strongly depends on their training, which is the process of adjusting their parameters. This process can be posed as an…
Recently reinforcement learning (RL) has emerged as a promising approach for quadrupedal locomotion, which can save the manual effort in conventional approaches such as designing skill-specific controllers. However, due to the complex…
Evolution Strategies (ES) are stochastic derivative-free optimization algorithms whose most prominent representative, the CMA-ES algorithm, is widely used to solve difficult numerical optimization problems. We provide the first rigorous…
Genetic Regulatory Networks (GRNs) plays a vital role in the understanding of complex biological processes. Modeling GRNs is significantly important in order to reveal fundamental cellular processes, examine gene functions and understanding…
An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the…
Regularized Auto-Encoders (RAEs) form a rich class of neural generative models. They effectively model the joint-distribution between the data and the latent space using an Encoder-Decoder combination, with regularization imposed in terms…
Evolutionary artificial neural networks (EANNs) refer to a special class of artificial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. Evolutionary algorithms are used to adapt…
Finding the optimal parameter setting (i.e. the optimal population size, the optimal mutation probability, the optimal evolutionary model etc) for an Evolutionary Algorithm (EA) is a difficult task. Instead of evolving only the parameters…
A key challenge to make effective use of evolutionary algorithms is to choose appropriate settings for their parameters. However, the appropriate parameter setting generally depends on the structure of the optimisation problem, which is…
Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved…
Evolution Strategies (ES) are effective gradient-free optimization methods that can be competitive with gradient-based approaches for policy search. ES only rely on the total episodic scores of solutions in their population, from which they…
Neuroevolution has recently been shown to be quite competitive in reinforcement learning (RL) settings, and is able to alleviate some of the drawbacks of gradient-based approaches. This paper will focus on applying neuroevolution using a…
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target…
Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the exploration potential of double actors remains underexplored.…
Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very…