English
Related papers

Related papers: From Past to Future: Rethinking Eligibility Traces

200 papers

Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward…

Machine Learning · Computer Science 2019-05-28 Hongyao Tang , Jianye Hao , Guangyong Chen , Pengfei Chen , Zhaopeng Meng , Yaodong Yang , Li Wang

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

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

Robotics · Computer Science 2024-12-19 Changxin Huang , Yanbin Chang , Junfan Lin , Junyang Liang , Runhao Zeng , Jianqiang Li

How much credit (or blame) should an action taken in a state get for a future reward? This is the fundamental temporal credit assignment problem in Reinforcement Learning (RL). One of the earliest and still most widely used heuristics is to…

Machine Learning · Computer Science 2022-06-07 Zeyu Zheng , Risto Vuorio , Richard Lewis , Satinder Singh

This paper investigates estimating the variance of a temporal-difference learning agent's update target. Most reinforcement learning methods use an estimate of the value function, which captures how good it is for the agent to be in a…

Artificial Intelligence · Computer Science 2018-02-15 Craig Sherstan , Brendan Bennett , Kenny Young , Dylan R. Ashley , Adam White , Martha White , Richard S. Sutton

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Machine Learning · Computer Science 2021-01-08 Kaige Yang

In reinforcement learning, the reward function on current state and action is widely used. When the objective is about the expectation of the (discounted) total reward only, it works perfectly. However, if the objective involves the total…

Artificial Intelligence · Computer Science 2018-12-03 Shuai Ma , Jia Yuan Yu

An agent's ability to leverage past experience is critical for efficiently solving new tasks. Approximate solutions for new tasks can be obtained from previously derived value functions, as demonstrated by research on transfer learning,…

Machine Learning · Computer Science 2023-09-06 Jacob Adamczyk , Stas Tiomkin , Rahul Kulkarni

In complex real-world tasks such as robotic manipulation and autonomous driving, collecting expert demonstrations is often more straightforward than specifying precise learning objectives and task descriptions. Learning from expert data can…

Robotics · Computer Science 2025-05-05 Daulet Baimukashev , Gokhan Alcan , Kevin Sebastian Luck , Ville Kyrki

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

We propose a framework for transferring any existing policy from a potentially unknown source MDP to a target MDP. This framework (1) enables reuse in the target domain of any form of source policy, including classical controllers,…

Machine Learning · Computer Science 2021-01-01 Daniel Graves , Jun Jin , Jun Luo

Learning depends on changes in synaptic connections deep inside the brain. In multilayer networks, these changes are triggered by error signals fed back from the output, generally through a stepwise inversion of the feedforward processing…

Neurons and Cognition · Quantitative Biology 2021-01-05 William F. Podlaski , Christian K. Machens

Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous. The present paper takes a generative perspective on policy evaluation via temporal-difference (TD)…

Machine Learning · Statistics 2021-12-03 Qin Lu , Georgios B. Giannakis

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Machine Learning · Computer Science 2025-06-16 Miguel Suau

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

This paper investigates the use of prior computation to estimate the value function to improve sample efficiency in on-policy policy gradient methods in reinforcement learning. Our approach is to estimate the value function from prior…

Machine Learning · Computer Science 2023-02-06 Md Masudur Rahman , Yexiang Xue

In reinforcement learning, Return, which is the weighted accumulated future rewards, and Value, which is the expected return, serve as the objective that guides the learning of the policy. In classic RL, return is defined as the…

Machine Learning · Computer Science 2020-10-27 Yufei Wang , Qiwei Ye , Tie-Yan Liu

In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game…

Machine Learning · Computer Science 2025-06-30 Alessandro Sestini , Joakim Bergdahl , Konrad Tollmar , Andrew D. Bagdanov , Linus Gisslén

Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the…

Artificial Intelligence · Computer Science 2018-04-13 André Barreto , Will Dabney , Rémi Munos , Jonathan J. Hunt , Tom Schaul , Hado van Hasselt , David Silver

We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment. This is achieved by equipping an agent…

Artificial Intelligence · Computer Science 2022-06-27 Geraud Nangue Tasse , Benjamin Rosman , Steven James