English
Related papers

Related papers: Adaptive Exploration for Multi-Reward Multi-Policy…

200 papers

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on…

Machine Learning · Computer Science 2025-10-23 Mohamad Louai Shehab , Antoine Aspeel , Necmiye Ozay

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

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

We present a Monte-Carlo simulation algorithm for real-time policy improvement of an adaptive controller. In the Monte-Carlo simulation, the long-term expected reward of each possible action is statistically measured, using the initial…

Machine Learning · Computer Science 2025-04-07 Gerald Tesauro , Gregory R. Galperin

We study sequential decision making in environments where rewards are only partially observed, but can be modeled as a function of observed contexts and the chosen action by the decision maker. This setting, known as contextual bandits,…

Methodology · Statistics 2015-03-11 Miroslav Dudík , Dumitru Erhan , John Langford , Lihong Li

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return…

Machine Learning · Computer Science 2020-03-05 Rituraj Kaushik , Konstantinos Chatzilygeroudis , Jean-Baptiste Mouret

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2023-01-05 Daniel Shin , Anca D. Dragan , Daniel S. Brown

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

The explore{exploit dilemma is one of the central challenges in Reinforcement Learning (RL). Bayesian RL solves the dilemma by providing the agent with information in the form of a prior distribution over environments; however, full…

Machine Learning · Computer Science 2012-03-19 Jonathan Sorg , Satinder Singh , Richard L. Lewis

We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of…

Machine Learning · Computer Science 2018-02-28 Ershad Banijamali , Yasin Abbasi-Yadkori , Mohammad Ghavamzadeh , Nikos Vlassis

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

In this paper, we discuss the deterministic policy gradient using the Actor-Critic methods based on the linear compatible advantage function approximator, where the input spaces are continuous. When the policy is restricted by hard…

Systems and Control · Electrical Eng. & Systems 2021-04-07 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Sebastien Gros

As search depth increases in autonomous reasoning and embodied planning, candidate action spaces expand exponentially, often exhausting computational budgets. While heuristic pruning is a critical countermeasure, existing approaches lack…

Machine Learning · Computer Science 2026-05-12 Tianhao Qian

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work…

Artificial Intelligence · Computer Science 2012-05-14 Kevin Regan , Craig Boutilier

We study the $(\varepsilon, \delta)$-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finite-time guarantees for approximate settings ($\varepsilon>0$) but suffer from high…

Machine Learning · Computer Science 2026-05-06 Cyrille Kone , Kevin Jamieson