English
Related papers

Related papers: BBQ-Networks: Efficient Exploration in Deep Reinfo…

200 papers

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural…

Artificial Intelligence · Computer Science 2017-11-21 Zachary Lipton , Xiujun Li , Jianfeng Gao , Lihong Li , Faisal Ahmed , Li Deng

We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance,…

Artificial Intelligence · Computer Science 2019-09-10 Kamyar Azizzadenesheli , Animashree Anandkumar

Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of…

Machine Learning · Computer Science 2016-07-05 Ian Osband , Charles Blundell , Alexander Pritzel , Benjamin Van Roy

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…

Machine Learning · Computer Science 2022-10-06 Fengdi Che , Xiru Zhu , Doina Precup , David Meger , Gregory Dudek

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

Machine Learning · Computer Science 2023-04-12 Qingfeng Lan , Yangchen Pan , Jun Luo , A. Rupam Mahmood

This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to…

Robotics · Computer Science 2025-04-23 Jun Wang , Hosein Hasanbeig , Kaiyuan Tan , Zihe Sun , Yiannis Kantaros

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new…

Machine Learning · Computer Science 2017-07-25 Tuomas Haarnoja , Haoran Tang , Pieter Abbeel , Sergey Levine

Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent.…

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these…

Machine Learning · Computer Science 2018-11-16 Raghuram Mandyam Annasamy , Katia Sycara

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Artificial Intelligence · Computer Science 2024-08-15 Pranav Putta , Edmund Mills , Naman Garg , Sumeet Motwani , Chelsea Finn , Divyansh Garg , Rafael Rafailov

In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning…

Machine Learning · Statistics 2017-12-04 Christopher Tegho , Paweł Budzianowski , Milica Gašić

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

Machine Learning · Computer Science 2010-09-15 Punit Pandey , Deepshikha Pandey , Shishir Kumar

The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against…

Artificial Intelligence · Computer Science 2022-07-08 Shivansh Beohar , Andrew Melnik

Reinforcement learning is a powerful technique for learning from trial and error, but it often requires a large number of interactions to achieve good performance. In some domains, such as sparse-reward tasks, an oracle that can provide…

Artificial Intelligence · Computer Science 2023-09-22 Zhourui Guo , Meng Yao , Yang Yu , Qiyue Yin

The use of mobile robots is being popular over the world mainly for autonomous explorations in hazardous/ toxic or unknown environments. This exploration will be more effective and efficient if the explorations in unknown environment can be…

Robotics · Computer Science 2011-10-11 Dip Narayan Ray , Somajyoti Majumder , Sumit Mukhopadhyay

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the…

Artificial Intelligence · Computer Science 2020-05-26 Rui Zhao , Volker Tresp

Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the…

Computation and Language · Computer Science 2016-09-29 Karthik Narasimhan , Adam Yala , Regina Barzilay

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences,…

Machine Learning · Statistics 2017-03-09 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…

Machine Learning · Computer Science 2012-05-14 John Asmuth , Lihong Li , Michael L. Littman , Ali Nouri , David Wingate

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Machine Learning · Computer Science 2019-11-21 Tom Blau , Lionel Ott , Fabio Ramos
‹ Prev 1 2 3 10 Next ›