A scalable species-based genetic algorithm for reinforcement learning problems
Reinforcement Learning (RL) methods often rely on gradient estimates to learn an optimal
policy for control problems. These expensive computations result in long training times, a …
policy for control problems. These expensive computations result in long training times, a …
Evolution-guided policy gradient in reinforcement learning
Abstract Deep Reinforcement Learning (DRL) algorithms have been successfully applied to
a range of challenging control tasks. However, these methods typically suffer from three core …
a range of challenging control tasks. However, these methods typically suffer from three core …
[PDF][PDF] Evolutionary reinforcement learning
Abstract Deep Reinforcement Learning (DRL) algorithms have been successfully applied to
a range of challenging control tasks. However, these methods typically suffer from three core …
a range of challenging control tasks. However, these methods typically suffer from three core …
Behavior-based neuroevolutionary training in reinforcement learning
J Stork, M Zaefferer, N Eisler, P Tichelmann… - Proceedings of the …, 2021 - dl.acm.org
In addition to their undisputed success in solving classical optimization problems,
neuroevolutionary and population-based algorithms have become an alternative to standard …
neuroevolutionary and population-based algorithms have become an alternative to standard …
Hyperparameter tuning for deep reinforcement learning applications
M Kiran, M Ozyildirim - arXiv preprint arXiv:2201.11182, 2022 - arxiv.org
Reinforcement learning (RL) applications, where an agent can simply learn optimal
behaviors by interacting with the environment, are quickly gaining tremendous success in a …
behaviors by interacting with the environment, are quickly gaining tremendous success in a …
Population based reinforcement learning
KW Pretorius, N Pillay - 2021 IEEE Symposium Series on …, 2021 - ieeexplore.ieee.org
Genetic algorithms have recently seen an increase in application due to their highly scalable
nature. Enabling more efficient utilization of processing power that has become readily …
nature. Enabling more efficient utilization of processing power that has become readily …
Adaptive Evolutionary Reinforcement Learning with Policy Direction
C Dong, D Li - Neural Processing Letters, 2024 - Springer
Abstract Evolutionary Reinforcement Learning (ERL) has garnered widespread attention in
recent years due to its inherent robustness and parallelism. However, the integration of …
recent years due to its inherent robustness and parallelism. However, the integration of …
Supplementing Gradient-Based Reinforcement Learning with Simple Evolutionary Ideas
H Khadilkar - arXiv preprint arXiv:2305.07571, 2023 - arxiv.org
We present a simple, sample-efficient algorithm for introducing large but directed learning
steps in reinforcement learning (RL), through the use of evolutionary operators. The …
steps in reinforcement learning (RL), through the use of evolutionary operators. The …
Effective diversity in population based reinforcement learning
J Parker-Holder, A Pacchiano… - Advances in …, 2020 - proceedings.neurips.cc
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 …
data they acquire in the environment. With that in mind, maintaining a population of agents is …
Effective Diversity in Population-Based Reinforcement Learning
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 …
data they acquire in the environment. With that in mind, maintaining a population of agents is …