English
Related papers

Related papers: Leveraging the Variance of Return Sequences for Ex…

200 papers

Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time.…

Machine Learning · Statistics 2011-09-22 Christos Dimitrakakis

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

We propose a exploration mechanism of policy in Deep Reinforcement Learning, which is exploring more when agent needs, called Add Noise to Noise (AN2N). The core idea is: when the Deep Reinforcement Learning agent is in a state of poor…

Machine Learning · Computer Science 2021-09-29 Youtian Guo , Qi Gao

We establish novel and general high-dimensional concentration inequalities and Berry-Esseen bounds for vector-valued martingales induced by Markov chains. We apply these results to analyze the performance of the Temporal Difference (TD)…

Machine Learning · Statistics 2026-05-22 Weichen Wu , Yuting Wei , Alessandro Rinaldo

While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to provide stronger learning signals and to enable applications…

Machine Learning · Computer Science 2026-03-05 Perry Dong , Chongyi Zheng , Chelsea Finn , Dorsa Sadigh , Benjamin Eysenbach

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent…

In this paper, a unified framework for exploration in reinforcement learning (RL) is proposed based on an option-critic model. The proposed framework learns to integrate a set of diverse exploration strategies so that the agent can…

Machine Learning · Computer Science 2024-09-10 Woojun Kim , Jeonghye Kim , Youngchul Sung

Temporal difference methods enable efficient estimation of value functions in reinforcement learning in an incremental fashion, and are of broader interest because they correspond learning as observed in biological systems. Standard value…

Machine Learning · Computer Science 2019-07-11 Brendan Bennett , Wesley Chung , Muhammad Zaheer , Vincent Liu

The exploration--exploitation trade-off in reinforcement learning (RL) is a well-known and much-studied problem that balances greedy action selection with novel experience, and the study of exploration methods is usually only considered in…

Machine Learning · Computer Science 2022-10-13 Jonathan C Balloch , Julia Kim , and Jessica L Inman , Mark O Riedl

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…

Machine Learning · Computer Science 2018-10-23 John Schulman , Philipp Moritz , Sergey Levine , Michael Jordan , Pieter Abbeel

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $\epsilon$-greedy. Motivated by this, we introduce $\beta$-DQN, a…

Machine Learning · Computer Science 2025-10-29 Hongming Zhang , Fengshuo Bai , Chenjun Xiao , Chao Gao , Bo Xu , Martin Müller

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

Machine Learning · Computer Science 2024-01-03 Guojian Wang , Faguo Wu , Xiao Zhang , Ning Guo , Zhiming Zheng

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

Machine Learning · Computer Science 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

Experience replay is a foundational technique in reinforcement learning that enhances learning stability by storing past experiences in a replay buffer and reusing them during training. Despite its practical success, its theoretical…

Machine Learning · Statistics 2025-11-14 Jiale Han , Xiaowu Dai , Yuhua Zhu

In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance…

Machine Learning · Computer Science 2013-10-15 Aviv Tamar , Dotan Di Castro , Shie Mannor

Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…

Machine Learning · Computer Science 2026-05-15 Théo Vincent , Kevin Gerhardt , Yogesh Tripathi , Habib Maraqten , Adam White , Martha White , Jan Peters , Carlo D'Eramo

Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic. Classical exploration strategies…

Machine Learning · Computer Science 2019-03-26 Nikolay Nikolov , Johannes Kirschner , Felix Berkenkamp , Andreas Krause

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are…

Machine Learning · Computer Science 2022-11-11 John D. Co-Reyes , Yingjie Miao , Daiyi Peng , Esteban Real , Sergey Levine , Quoc V. Le , Honglak Lee , Aleksandra Faust