paper-with-me

Papers

Averaging $n$-step Returns Reduces Variance in Reinforcement Learning

2024-02-06 · Brett Daley, Martha White, Marlos C. Machado

Multistep returns, such as $n$-step returns and $\lambda$-returns, are commonly used to improve the sample efficiency of reinforcement learning (RL) methods. The variance of the multistep returns becomes the limiting factor in their length; looking too far into the future increases variance and reverses the benefits of multistep learning. In our work, we demonstrate the ability of compound returns -- weighted averages of $n$-step returns -- to reduce variance. We prove for the first time that any compound return with the same contraction modulus as a given $n$-step return has strictly lower variance. We additionally prove that this variance-reduction property improves the finite-sample complexity of temporal-difference learning under linear function approximation. Because general compound returns can be expensive to implement, we introduce two-bootstrap returns which reduce variance while remaining efficient, even when using minibatched experience replay. We conduct experiments showing that compound returns often increase the sample efficiency of $n$-step deep RL agents like DQN and PPO.

📄 PDF Abstract BibTeX arXiv:2402.03903

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Entropy Regularization 설명 없음
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

SACn: Soft Actor-Critic with n-step Returns

2025-12-15 · Jakub Łyskawa, Jakub Lewandowski, Paweł Wawrzyński arxiv

Soft Actor-Critic (SAC) is widely used in practical applications and is now one of the most relevant off-policy online model-free reinforcement learning (RL) methods. The technique of n-step returns is known to increase …

Reinforcement Learning

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

2025-03-05 · Dong Tian, Ge Li, Hongyi Zhou, Onur Celik 외

Soft Actor-Critic (SAC) critically depends on its critic network, which typically evaluates a single state-action pair to guide policy updates. Using N-step returns is a common practice to reduce the bias in the target v…

Chunking

Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging

2017-09-12 · Chandrashekar Lakshminarayanan, Csaba Szepesvári

We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinfor…

Reinforcement LearningReinforcement Learning (RL)

Mixture of Step Returns in Bootstrapped DQN

2020-07-16 · Po-Han Chiang, Hsuan-Kung Yang, Zhang-Wei Hong, Chun-Yi Lee

The concept of utilizing multi-step returns for updating value functions has been adopted in deep reinforcement learning (DRL) for a number of years. Updating value functions with different backup lengths provides advant…

Deep Reinforcement Learning

Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning

2017-05-21 · ICLR 2018 1 · Sahil Sharma, Girish Raguvir J, Srivatsan Ramesh, Balaraman Ravindran

Reinforcement Learning (RL) can model complex behavior policies for goal-directed sequential decision making tasks. A hallmark of RL algorithms is Temporal Difference (TD) learning: value function for the current state i…

BenchmarkingDecision MakingDeep Reinforcement Learningreinforcement-learning+3