OpenAI Blog April 18, 2018

Evolved Policy Gradients

We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. Agents trained with EPG can succeed at basic tasks at test time that were outside their training regime, like learning to navigate to an object on a different side of the room from where it was placed during training.

Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.

agents

OpenAI Blog

Mar 24, 2017

Evolution strategies as a scalable alternative to reinforcement learning

We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e. g.

reinforcement-learning benchmarks

arXiv AI

Jun 26

EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning

arXiv:2606. 26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed.

By Boyun Zhang, Chao Wang, Kai Wu

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 11

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

arXiv:2604. 01499v2 Announce Type: replace Abstract: Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space.

By William Hoy, Binxu Wang, Xu Pan

llms reinforcement-learning fine-tuning

arXiv AI

Jun 3

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

arXiv:2606. 03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static.

By Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye

llms agents reinforcement-learning

arXiv AI

Jun 18

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

arXiv:2606. 18388v1 Announce Type: cross Abstract: RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization parameters predominantly oscillate in response to shifting training dynamics.

By Haoyang Fang, Wei Zhu, Boran Han, Alex Zhang, Zhenyu Pan, Shuo Yang, Shuai Zhang, Jiading Gai, Peng Tang, Cuixiong Hu, Xuan Zhu, Huzefa Rangwala, George Karypis, Bernie Wang

llms agents reinforcement-learning

arXiv Machine Learning

5d ago

Trajectory First: A Curriculum for Discovering Diverse Policies

arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.

By Cornelius V. Braun, Sayantan Auddy, Marc Toussaint

agents reinforcement-learning robotics safety

Related stories

Evolution strategies as a scalable alternative to reinforcement learning

EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

Trajectory First: A Curriculum for Discovering Diverse Policies