Policy Optimization by Genetic Distillation
Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly due to the catastrophic consequence of parameter crossovers of neural networks. Here, we present Genetic Policy Optimization (GPO), a new genetic algorithm for sample-efficient deep policy optimization. GPO uses imitation learning for policy crossover in the state space and applies policy gradient methods for mutation. Our experiments on MuJoCo tasks show that GPO as a genetic algorithm is able to provide superior performance over the state-of-the-art policy gradient methods and achieves comparable or higher sample efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningImitation LearningMuJoCoPolicy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Monte-Carlo Tree Search for Policy Optimization
Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolut…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important for successive model generations and multi-domain consolidation, wher…
Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
The challenge of discovering new molecules with desired properties is crucial in domains like drug discovery and material design. Recent advances in deep learning-based generative methods have shown promise but face the …
Bayesian OptimizationDrug Discoveryβ-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reliably often requires substantial engineering effort. We identify a st…
Mathematical ReasoningReinforcement LearningORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation
We introduce ORPO-Distill, a general-purpose method for cross-architecture LLM distillation that formulates the problem as a preference optimization task. Unlike standard CoT distillation, the approach transfers knowledg…