# Harnessing Bounded-Support Evolution Strategies for Policy Refinement

arXiv: https://arxiv.org/abs/2511.09923 · HTML: https://mlsanity.com/paper/2511.09923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Builds on (most cited first, 30 of 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Challenges of Real-World Reinforcement Learning](https://mlsanity.com/paper/1904.12901/) (2019)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO](https://mlsanity.com/paper/2005.12729/) (2020)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents](https://mlsanity.com/paper/1712.06560/) (2017)
- [Benchmarking Reinforcement Learning Algorithms on Real-World Robots](https://mlsanity.com/paper/1809.07731/) (2018)
- [CEM-RL: Combining evolutionary and gradient-based methods for policy search](https://mlsanity.com/paper/1810.01222/) (2018)
- [Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors](https://mlsanity.com/paper/2305.04412/) (2023)
- [Evolutionary Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.04150/) (2023)
- [Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey](https://mlsanity.com/paper/2110.01411/) (2021)
- [Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey](https://mlsanity.com/paper/2203.14009/) (2022)
- [Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem](https://mlsanity.com/paper/2402.02868/) (2024)
- [So You Think You Can Scale Up Autonomous Robot Data Collection?](https://mlsanity.com/paper/2411.01813/) (2024)
- [Efficacy of Modern Neuro-Evolutionary Strategies for Continuous Control Optimization](https://mlsanity.com/paper/1912.05239/) (2019)
- [Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm](https://mlsanity.com/paper/1807.03392/) (2018)
- [Evolutionary Reinforcement Learning: A Systematic Review and Future Directions](https://mlsanity.com/paper/2402.13296/) (2024)
- [Evolutionary Policy Optimization](https://mlsanity.com/paper/2503.19037/) (2025)

## Abstract (arXiv)

Improving competent robot policies with on-policy RL is often hampered by noisy, low-signal gradients. We revisit Evolution Strategies (ES) as a policy-gradient proxy and localize exploration with bounded, antithetic triangular perturbations, suitable for policy refinement. We propose Triangular-Distribution ES (TD-ES) which pairs bounded triangular noise with a centered-rank finite-difference estimator to deliver stable, parallelizable, gradient-free updates. In a two-stage pipeline - PPO pretraining followed by TD-ES refinement - this preserves early sample efficiency while enabling robust late-stage gains. Across a suite of robotic manipulation tasks, TD-ES raises success rates by 26.5% relative to PPO and greatly reduces variance, offering a simple, compute-light path to reliable refinement.