- Ackley, D. and Littman, M., 1991. Interactions between learning and evolution. Artificial Life, 10, pp.487-509.
- Zhang, X., Gao, X., Wu, K. and Pan, Z., 2024. Learning neural traffic rules. IEEE Robotics and Automation Letters.
https://www.cs.ox.ac.uk/people/shimon.whiteson/pubs/whitesonrlsota11.pdf
https://link.springer.com/article/10.1007/s12065-011-0066-z
https://www.ifaamas.org/Proceedings/aamas2010/pdf/01%20Full%20Papers/15_04_FP_0630.pdf
https://dl.acm.org/doi/10.1145/1569901.1570064
https://www.sciencedirect.com/science/article/pii/S0196677409000364
https://dl.acm.org/doi/10.1145/1553374.1553426
https://link.springer.com/chapter/10.1007/11871842_64
https://link.springer.com/article/10.1023/A:1018004120707
https://ieeexplore.ieee.org/document/155416
https://link.springer.com/article/10.1007/s10458-009-9100-2
https://arxiv.org/abs/1712.00006
https://openai.com/research/better-exploration-with-parameter-noise
https://www.ijcai.org/Proceedings/99-2/Papers/097.pdf
https://dl.acm.org/doi/10.1145/1068009.1068092
https://link.springer.com/chapter/10.1007/11550907_61
https://jmlr.org/papers/v7/whiteson06a.html
https://www.jmlr.org/papers/v11/verbancsics10a.html
https://dl.acm.org/doi/10.1145/2463372.2463509
https://arxiv.org/abs/1703.03864
https://www.deepmind.com/publications/noisy-networks-for-exploration
https://www.ijcai.org/Proceedings/2019/0295.pdf
http://proceedings.mlr.press/v80/colas18a.html
https://aamas.csc.liv.ac.uk/Proceedings/aamas2020/pdfs/p1738.pdf
https://www.science.org/doi/10.1126/science.aau6249
http://proceedings.mlr.press/v48/duan16.html
Bootstrapping Q-Learning for Robotics From Neuro-Evolution Results
https://www.cs.ubc.ca/~murphyk/Papers/pomdp.pdf
[1994] Evolving Neural Networks to Focus Minimax Search [AAAI+Miikkulainen]
[1996] Evolving Obstacle Avoidance Behavior in a Robot Arm [Miikkulainen]
[1999] Evolution of Goal-Directed Behavior from Limited Information in a Complex Environment [GECCO+CMU+Sycara]
[2020] Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination [ICML+Tumer]
[2021] Evolutionary Game Theory Squared - Evolving Agents in Endogenously Evolving Games [AAAI+Washington]
[2001] Robot Weightlifting By Direct Policy Search [IJCAI+Barto]
[2003] Real-time Adaptation Technique to Real Robots - An Experiment with a Humanoid Robot [CEC+Tokyo+Iba]
[2004] Efficient Evolution of Neural Networks through Complexification [PhD+Stanley+Miikkulainen]
[2005] Synergies between Evolutionary and Neural Computation [Igel]
[2005] The Quantitative Law of Effect is a Robust Emergent Property of an Evolutionary Algorithm for Reinforcement Learning
[2007] Adaptive Representations for Reinforcement Learning [PhD+Whiteson+Stone]
[2008] Similarities and Differences between Policy Gradient Methods and Evolution Strategies [Igel]
[2009] Neuroevolutionary Reinforcement Learning for Generalized Helicopter Control [GECCO+Amsterdam+Whiteson]
[2010] On the Characteristics of Sequential Decision Problems and Their Impact on Evolutionary Computation and Reinforcement Learning
[2011] Neuroevolutionary Reinforcement Learning for Generalized Control of Simulated Helicopters [Whiteson]
[2012] Reinforcement Learning in Continuous State and Action Spaces
[2020] Momentum Accelerates Evolutionary Dynamics [Google]
[2020] Visualizing Movement Control Optimization Landscapes [IEEE-TVCG+Stanford]
[2020] Robust Reinforcement Learning using Adversarial Populations [Berkeley+Abbeel]
[2018] Challenges in High-Dimensional Reinforcement Learning with Evolution Strategies [PPSN+Glasmachers]
[2019] Neuroevolution for Deep Reinforcement Learning Problems [GECCO+GoogleBrain+Ha]
[2019] CEM-RL - Combining evolutionary and gradient-based methods for policy search [ICLR+Sigaud]
[2019] Neural Graph Evolution - Towards Efficient Automatic Robot Design [ICLR+Toronto+NVIDIA+Ba]
[2020] Learning to Guide Random Search [ICLR+IntelLabs]
[1993] Genetic Reinforcement Learning for Neurocontrol Problems [ML+Whitley]
[1999] Evolution, Neural Networks, Games, and Intelligence [PIEEE+Fogel]
[2011] Cross-Entropy Randomized Motion Planning [RSS]
[2012] Path Integral Policy Improvement with Covariance Matrix Adaptation [ICML+Stulp+Sigaud]
[2012] Policy Improvement Methods - Between Black-Box Optimization and Episodic Reinforcement Learning [Stulp+Sigaud]
[2018] Deep Neuroevolution - Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning [OpenReview+UberAI+Stanley+Clune]
[2018] Policy Optimization by Genetic Distillation [ICLR]
[2018] Simple Random Search of Static Linear Policies is Competitive for Reinforcement Learning [NeurIPS+Berkeley+SM]
[2019] Computers Evolve a New Path Toward Human Intelligence [quantamagazine]
[2019] Designing Neural Networks through Neuroevolution [Stanley+Clune+Miikkulainen+NatureMachineIntelligence]
[2020] Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing [AAMAS+Glasmachers]