Search Results for author:
Found 13 papers, 9 papers with code
Evolution Transformer: In-Context Evolutionary Optimization
Given a trajectory of evaluations and search distribution statistics, Evolution Transformer outputs a performance-improving update to the search distribution.
Large Language Models As Evolution Strategies
Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms.
Discovering Temporally-Aware Reinforcement Learning Algorithms
We propose a simple augmentation to two existing objective discovery approaches that allows the discovered algorithm to dynamically update its objective function throughout the agent's training procedure, resulting in expressive schedules and increased generalization across different training horizons.
JaxMARL: Multi-Agent RL Environments in JAX
This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL.
NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications
Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e. g. meta-learning through long inner loop unrolls or optimizing non-differentiable operators.
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization?
Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution.
evosax: JAX-based Evolution Strategies
In order to better harness these resources and to enable the next generation of black-box optimization algorithms, we release evosax: A JAX-based library of evolution strategies which allows researchers to leverage powerful function transformations such as just-in-time compilation, automatic vectorization and hardware parallelization.
Discovering Evolution Strategies via Meta-Black-Box Optimization
Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies.
On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning
But how is the performance of winning lottery tickets affected by the distributional shift inherent to reinforcement learning problems?
Learning Not to Learn: Nature versus Nurture in Silico
Animals are equipped with a rich innate repertoire of sensory, behavioral and motor skills, which allows them to interact with the world immediately after birth.
Reinforcement Learning with Structured Hierarchical Grammar Representations of Actions
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences.
Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions
By treating an on-policy trajectory as a sentence sampled from the policy-conditioned language of the environment, we identify hierarchical constituents with the help of unsupervised grammatical inference.
