English
Related papers

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

200 papers

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach…

Machine Learning · Computer Science 2024-09-23 Daniel Russo

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and…

Robotics · Computer Science 2021-05-04 Saeed Tafazzol , Erfan Fathi , Mahdi Rezaei , Ehsan Asali

We consider the problem of continuous-time policy evaluation. This consists in learning through observations the value function associated with an uncontrolled continuous-time stochastic dynamic and a reward function. We propose two…

Machine Learning · Computer Science 2023-06-08 Ziad Kobeissi , Francis Bach

Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be…

Machine Learning · Computer Science 2026-02-16 Abdul Wahab , Raksha Kumaraswamy , Martha White

The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existing exploration methods are mostly based on adding noise to…

Machine Learning · Computer Science 2018-03-28 Tianbing Xu , Qiang Liu , Liang Zhao , Jian Peng

In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal…

Machine Learning · Computer Science 2025-09-05 Mahammad Humayoo

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or…

Machine Learning · Computer Science 2025-03-21 Claire Chen , Shuze Daniel Liu , Shangtong Zhang

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned…

Machine Learning · Computer Science 2019-04-15 Kaleigh Clary , Emma Tosch , John Foley , David Jensen

Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the…

Machine Learning · Computer Science 2018-10-02 Gino Brunner , Manuel Fritsche , Oliver Richter , Roger Wattenhofer

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward problems, the reward is rare, which means that the agent will…

Machine Learning · Computer Science 2022-05-03 Pawel Ladosz , Lilian Weng , Minwoo Kim , Hyondong Oh

Temporal difference (TD) learning is a cornerstone reinforcement learning (RL) method for policy evaluation, where the goal is to estimate the value function of a Markov decision process under a fixed policy. While a substantial body of…

Machine Learning · Computer Science 2026-02-02 Donghwan Lee , Do Wan Kim

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly,…

Machine Learning · Computer Science 2026-01-23 Ofir Nabati , Guy Tennenholtz , Shie Mannor

Exploration in complex domains is a key challenge in reinforcement learning, especially for tasks with very sparse rewards. Recent successes in deep reinforcement learning have been achieved mostly using simple heuristic exploration…

Machine Learning · Computer Science 2017-03-07 Joshua Achiam , Shankar Sastry

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the…

Computation and Language · Computer Science 2019-03-26 Prithviraj Ammanabrolu , Mark O. Riedl

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Machine Learning · Computer Science 2019-12-30 Qisheng Wang , Qichao Wang

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse…

Machine Learning · Computer Science 2026-03-04 Naoki Shitanda , Motoki Omura , Tatsuya Harada , Takayuki Osa

Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The…

Machine Learning · Computer Science 2019-07-01 Weichang Wu , Junchi Yan , Xiaokang Yang , Hongyuan Zha

Recent research on structured exploration placed emphasis on identifying novel states in the state space and incentivizing the agent to revisit them through intrinsic reward bonuses. In this study, we question whether the performance boost…

Machine Learning · Computer Science 2020-11-12 Sneha Aenugu