Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces large bias in tasks with high action dimensions, and bias from clipping makes it difficult to reuse old samples with large IS weights. In this paper, we consider PPO, a representative on-policy algorithm, and propose its improvement by dimension-wise IS weight clipping which separately clips the IS weight of each action dimension to avoid large bias and adaptively controls the IS weight to bound policy update from the current policy. This new technique enables efficient learning for high action-dimensional tasks and reusing of old samples like in off-policy learning to increase the sample efficiency. Numerical results show that the proposed new algorithm outperforms PPO and other RL algorithms in various Open AI Gym tasks.
Code (1)
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present …
Reinforcement LearningMathematical ReasoningGIPO: Gaussian Importance Sampling Policy Optimization
Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor data efficiency, particularly in settings …
Reinforcement LearningClip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL
We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping on the importance-sampling (IS) weight. We study RL methods with sequence-le…
Reinforcement LearningAdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
Differential privacy has been proven effective for stochastic gradient descent; however, existing methods often suffer from performance degradation in high-dimensional settings, as the scale of injected noise increases w…
Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation
Existing off-policy reinforcement learning algorithms often rely on an explicit state-action-value function representation, which can be problematic in high-dimensional action spaces due to the curse of dimensionality. T…
Deep Reinforcement LearningEfficient Explorationreinforcement-learning