Search Results for author: Mohammad Ghavamzadeh

Found 85 papers, 16 papers with code

Adaptive Sampling for Estimating Probability Distributions

no code implementations ICML 2020 Shubhanshu Shekhar, Tara Javidi, Mohammad Ghavamzadeh

We consider the problem of allocating a fixed budget of samples to a finite set of discrete distributions to learn them uniformly well (minimizing the maximum error) in terms of four common distance measures: $\ell_2^2$, $\ell_1$, $f$-divergence, and separation distance.

Aligning Text-to-Image Models using Human Feedback

no code implementations23 Feb 2023 Kimin Lee, Hao liu, MoonKyung Ryu, Olivia Watkins, Yuqing Du, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Shixiang Shane Gu

Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.

Image Generation

Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management

no code implementations21 Feb 2023 Dhawal Gupta, Yinlam Chow, Mohammad Ghavamzadeh, Craig Boutilier

By exploiting MoE-LM structure, our methods significantly reduce the size of the action space and improve the efficacy of RL-based DM.

Dialogue Management Management +2

Multi-Task Off-Policy Learning from Bandit Feedback

no code implementations9 Dec 2022 Joey Hong, Branislav Kveton, Sumeet Katariya, Manzil Zaheer, Mohammad Ghavamzadeh

We prove per-task bounds on the suboptimality of the learned policies, which show a clear improvement over not using the hierarchical model.

Learning-To-Rank Recommendation Systems

Operator Splitting Value Iteration

no code implementations25 Nov 2022 Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-Massoud Farahmand

We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function.

reinforcement-learning Reinforcement Learning (RL)

RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk

no code implementations9 Sep 2022 Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh, Reazul Russel

We propose and analyze a new framework to jointly model the risk associated with epistemic and aleatory uncertainties in finite-horizon and discounted infinite-horizon MDPs.

Reinforcement Learning (RL) Safe Reinforcement Learning

Robust Reinforcement Learning using Offline Data

1 code implementation10 Aug 2022 Kishan Panaganti, Zaiyan Xu, Dileep Kalathil, Mohammad Ghavamzadeh

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters.

reinforcement-learning Reinforcement Learning (RL)

A Mixture-of-Expert Approach to RL-based Dialogue Management

no code implementations31 May 2022 Yinlam Chow, Aza Tulepbergenov, Ofir Nachum, MoonKyung Ryu, Mohammad Ghavamzadeh, Craig Boutilier

Despite recent advancements in language models (LMs), their application to dialogue management (DM) problems and ability to carry on rich conversations remain a challenge.

Dialogue Management Language Modelling +2

Multi-Environment Meta-Learning in Stochastic Linear Bandits

no code implementations12 May 2022 Ahmadreza Moradipari, Mohammad Ghavamzadeh, Taha Rajabzadeh, Christos Thrampoulidis, Mahnoosh Alizadeh

In this work we investigate meta-learning (or learning-to-learn) approaches in multi-task linear stochastic bandit problems that can originate from multiple environments.


Collaborative Multi-agent Stochastic Linear Bandits

no code implementations12 May 2022 Ahmadreza Moradipari, Mohammad Ghavamzadeh, Mahnoosh Alizadeh

We propose a distributed upper confidence bound (UCB) algorithm and prove a high probability bound on its $T$-round regret in which we include a linear growth of regret associated with each communication round.

Efficient Risk-Averse Reinforcement Learning

1 code implementation10 May 2022 Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns.

Autonomous Driving reinforcement-learning +1

Meta-Learning for Simple Regret Minimization

1 code implementation25 Feb 2022 MohammadJavad Azizi, Branislav Kveton, Mohammad Ghavamzadeh, Sumeet Katariya

This is while we show that the meta simple regret of the frequentist algorithm is $\tilde{O}(\sqrt{m} n + m/ \sqrt{n})$, and thus, worse.


Deep Hierarchy in Bandits

no code implementations3 Feb 2022 Joey Hong, Branislav Kveton, Sumeet Katariya, Manzil Zaheer, Mohammad Ghavamzadeh

We use this exact posterior to analyze the Bayes regret of HierTS in Gaussian bandits.

Thompson Sampling

Hierarchical Bayesian Bandits

no code implementations12 Nov 2021 Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh

We provide a unified view of all these problems, as learning to act in a hierarchical Bayesian bandit.

Federated Learning Thompson Sampling

Thompson Sampling with a Mixture Prior

no code implementations10 Jun 2021 Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh, Craig Boutilier

We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution.

Decision Making Multi-Task Learning +3

Fixed-Budget Best-Arm Identification in Structured Bandits

no code implementations9 Jun 2021 Mohammad Javad Azizi, Branislav Kveton, Mohammad Ghavamzadeh

We analyze our algorithm in linear and generalized linear models (GLMs) and propose a practical implementation based on a G-optimal design.

Multi-Armed Bandits

Feature and Parameter Selection in Stochastic Linear Bandits

no code implementations9 Jun 2021 Ahmadreza Moradipari, Berkay Turan, Yasin Abbasi-Yadkori, Mahnoosh Alizadeh, Mohammad Ghavamzadeh

In the second setting, the reward parameter of the LB problem is arbitrarily selected from $M$ models represented as (possibly) overlapping balls in $\mathbb R^d$.

Model Selection

Adaptive Sampling for Minimax Fair Classification

no code implementations NeurIPS 2021 Shubhanshu Shekhar, Greg Fields, Mohammad Ghavamzadeh, Tara Javidi

Machine learning models trained on uncurated datasets can often end up adversely affecting inputs belonging to underrepresented groups.

Classification General Classification

Non-Stationary Latent Bandits

no code implementations1 Dec 2020 Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed, Mohammad Ghavamzadeh, Craig Boutilier

The key idea is to frame this problem as a latent bandit, where the prototypical models of user behavior are learned offline and the latent state of the user is inferred online from its interactions with the models.

Recommendation Systems Thompson Sampling

Soft-Robust Algorithms for Batch Reinforcement Learning

no code implementations30 Nov 2020 Elita A. Lobo, Mohammad Ghavamzadeh, Marek Petrik

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure.

Decision Making reinforcement-learning +1

Variance-Reduced Off-Policy Memory-Efficient Policy Search

no code implementations14 Sep 2020 Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh, Hengshuai Yao, Tianbao Yang, Bo Liu

To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples.

Reinforcement Learning (RL) Stochastic Optimization

Deep Bayesian Quadrature Policy Optimization

1 code implementation28 Jun 2020 Akella Ravi Tej, Kamyar Azizzadenesheli, Mohammad Ghavamzadeh, Anima Anandkumar, Yisong Yue

On the other hand, more sample efficient alternatives like Bayesian quadrature methods have received little attention due to their high computational complexity.

Continuous Control Policy Gradient Methods

Control-Aware Representations for Model-based Reinforcement Learning

no code implementations ICLR 2021 Brandon Cui, Yin-Lam Chow, Mohammad Ghavamzadeh

We first formulate a LCE model to learn representations that are suitable to be used by a policy iteration style algorithm in the latent space.

Model-based Reinforcement Learning reinforcement-learning +2

Stochastic Bandits with Linear Constraints

no code implementations17 Jun 2020 Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett, Heinrich Jiang

We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB), and prove an $\widetilde{\mathcal{O}}(\frac{d\sqrt{T}}{\tau-c_0})$ bound on its $T$-round regret, where the denominator is the difference between the constraint threshold and the cost of a known feasible action.

Multi-Armed Bandits

Variational Model-based Policy Optimization

no code implementations9 Jun 2020 Yin-Lam Chow, Brandon Cui, MoonKyung Ryu, Mohammad Ghavamzadeh

Model-based reinforcement learning (RL) algorithms allow us to combine model-generated data with those collected from interaction with the real system in order to alleviate the data efficiency problem in RL.

Continuous Control Model-based Reinforcement Learning +1

Neural Lyapunov Redesign

1 code implementation6 Jun 2020 Arash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf

We provide theoretical results on the class of systems that can be treated with the proposed algorithm and empirically evaluate the effectiveness of our method using an exemplary dynamical system.

Finite-Sample Analysis of Proximal Gradient TD Algorithms

no code implementations6 Jun 2020 Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms.

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

1 code implementation6 Jun 2020 Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms.

reinforcement-learning Reinforcement Learning (RL)

Mirror Descent Policy Optimization

1 code implementation ICLR 2022 Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh

Overall, MDPO is derived from the MD principles, offers a unified approach to viewing a number of popular RL algorithms, and performs better than or on-par with TRPO, PPO, and SAC in a number of continuous control tasks.

Continuous Control Reinforcement Learning (RL)

Active Model Estimation in Markov Decision Processes

no code implementations6 Mar 2020 Jean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta, Mohammad Ghavamzadeh, Alessandro Lazaric

Using a number of simple domains with heterogeneous noise in their transitions, we show that our heuristic-based algorithm outperforms both our original algorithm and the maximum entropy algorithm in the small sample regime, while achieving similar asymptotic performance as that of the original algorithm.

Common Sense Reasoning Efficient Exploration

Predictive Coding for Locally-Linear Control

1 code implementation ICML 2020 Rui Shu, Tung Nguyen, Yin-Lam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung H. Bui

High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks.

Decision Making

Policy-Aware Model Learning for Policy Gradient Methods

1 code implementation28 Feb 2020 Romina Abachi, Mohammad Ghavamzadeh, Amir-Massoud Farahmand

This is in contrast to conventional model learning approaches, such as those based on maximum likelihood estimate, that learn a predictive model of the environment without explicitly considering the interaction of the model and the planner.

Model-based Reinforcement Learning Policy Gradient Methods

Conservative Exploration in Reinforcement Learning

no code implementations8 Feb 2020 Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward.

reinforcement-learning Reinforcement Learning (RL)

Improved Algorithms for Conservative Exploration in Bandits

no code implementations8 Feb 2020 Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta

In this case, it is desirable to deploy online learning algorithms (e. g., a multi-armed bandit algorithm) that interact with the system to learn a better/optimal policy under the constraint that during the learning process the performance is almost never worse than the performance of the baseline itself.

Marketing Recommendation Systems

Adaptive Sampling for Estimating Multiple Probability Distributions

no code implementations28 Oct 2019 Shubhanshu Shekhar, Tara Javidi, Mohammad Ghavamzadeh

We consider the problem of allocating samples to a finite set of discrete distributions in order to learn them uniformly well in terms of four common distance measures: $\ell_2^2$, $\ell_1$, $f$-divergence, and separation distance.

Multi-step Greedy Reinforcement Learning Algorithms

no code implementations ICML 2020 Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh

We derive model-free RL algorithms based on $\kappa$-PI and $\kappa$-VI in which the surrogate problem can be solved by any discrete or continuous action RL method, such as DQN and TRPO.

Continuous Control Game of Go +3

Benchmarking Batch Deep Reinforcement Learning Algorithms

4 code implementations3 Oct 2019 Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh, Joelle Pineau

Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment.

Benchmarking Q-Learning +2

Safe Policy Learning for Continuous Control

no code implementations25 Sep 2019 Yinlam Chow, Ofir Nachum, Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i. e.,~policies that keep the agent in desirable situations, both during training and at convergence.

Continuous Control

Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning

no code implementations25 Sep 2019 Yonathan Efroni, Manan Tomar, Mohammad Ghavamzadeh

In this work, we explore the benefits of multi-step greedy policies in model-free RL when employed in the framework of multi-step Dynamic Programming (DP): multi-step Policy and Value Iteration.

Continuous Control Game of Go +3

Online Planning with Lookahead Policies

no code implementations NeurIPS 2020 Yonathan Efroni, Mohammad Ghavamzadeh, Shie Mannor

This is the first work that proves improved sample complexity as a result of {\em increasing} the lookahead horizon in online planning.

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

1 code implementation ICLR 2020 Nir Levine, Yin-Lam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui

A promising approach is to embed the high-dimensional observations into a lower-dimensional latent representation space, estimate the latent dynamics model, then utilize this model for control in the latent space.

Decision Making Representation Learning

Randomized Exploration in Generalized Linear Bandits

no code implementations21 Jun 2019 Branislav Kveton, Manzil Zaheer, Csaba Szepesvari, Lihong Li, Mohammad Ghavamzadeh, Craig Boutilier

GLM-TSL samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution.

Active Learning for Binary Classification with Abstention

no code implementations1 Jun 2019 Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi

We construct and analyze active learning algorithms for the problem of binary classification with abstention.

Active Learning Classification +1

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

1 code implementation NeurIPS 2019 Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor

In this paper, we focus on model-based RL in the finite-state finite-horizon MDP setting and establish that exploring with \emph{greedy policies} -- act by \emph{1-step planning} -- can achieve tight minimax performance in terms of regret, $\tilde{\mathcal{O}}(\sqrt{HSAT})$.

Model-based Reinforcement Learning reinforcement-learning +1

Binary Classification with Bounded Abstention Rate

no code implementations23 May 2019 Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi

We then propose a plug-in classifier that employs unlabeled samples to decide the region of abstention and derive an upper-bound on the excess risk of our classifier under standard \emph{H\"older smoothness} and \emph{margin} assumptions.

Classification General Classification

Perturbed-History Exploration in Stochastic Linear Bandits

no code implementations21 Mar 2019 Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Craig Boutilier

Our algorithm, perturbed-history exploration in a linear bandit (LinPHE), estimates a linear model from its perturbed history and pulls the arm with the highest value under that model.

Perturbed-History Exploration in Stochastic Multi-Armed Bandits

no code implementations26 Feb 2019 Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Craig Boutilier

Finally, we empirically evaluate PHE and show that it is competitive with state-of-the-art baselines.

Multi-Armed Bandits

Lyapunov-based Safe Policy Optimization for Continuous Control

1 code implementation28 Jan 2019 Yin-Lam Chow, Ofir Nachum, Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh

We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them.

Continuous Control Robot Navigation

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

no code implementations13 Nov 2018 Branislav Kveton, Csaba Szepesvari, Sharan Vaswani, Zheng Wen, Mohammad Ghavamzadeh, Tor Lattimore

Specifically, it pulls the arm with the highest mean reward in a non-parametric bootstrap sample of its history with pseudo rewards.

Multi-Armed Bandits

Lyapunov-based Safe Policy Optimization

no code implementations27 Sep 2018 Yinlam Chow, Ofir Nachum, Mohammad Ghavamzadeh, Edgar Guzman-Duenez

In many reinforcement learning applications, it is crucial that the agent interacts with the environment only through safe policies, i. e.,~policies that do not take the agent to certain undesirable situations.

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization

no code implementations NeurIPS 2018 Bo Liu, Tengyang Xie, Yangyang Xu, Mohammad Ghavamzadeh, Yin-Lam Chow, Daoming Lyu, Daesub Yoon

Risk management in dynamic decision problems is a primary concern in many fields, including financial investment, autonomous driving, and healthcare.

Autonomous Driving Management

Risk-Sensitive Generative Adversarial Imitation Learning

no code implementations13 Aug 2018 Jonathan Lacotte, Mohammad Ghavamzadeh, Yin-Lam Chow, Marco Pavone

We then derive two different versions of our RS-GAIL optimization problem that aim at matching the risk profiles of the agent and the expert w. r. t.

Imitation Learning

A Lyapunov-based Approach to Safe Reinforcement Learning

1 code implementation NeurIPS 2018 Yin-Lam Chow, Ofir Nachum, Edgar Duenez-Guzman, Mohammad Ghavamzadeh

In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints.

Decision Making reinforcement-learning +2

Optimizing over a Restricted Policy Class in Markov Decision Processes

no code implementations26 Feb 2018 Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh, Nikos Vlassis

However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an efficient algorithm that finds a policy that is almost as good as the best convex combination of the base policies.

Policy Gradient Methods

More Robust Doubly Robust Off-policy Evaluation

no code implementations ICML 2018 Mehrdad Farajtabar, Yin-Lam Chow, Mohammad Ghavamzadeh

In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time.

Multi-Armed Bandits Off-policy evaluation

Path Consistency Learning in Tsallis Entropy Regularized MDPs

no code implementations ICML 2018 Ofir Nachum, Yin-Lam Chow, Mohammad Ghavamzadeh

In this paper, we follow the work of Nachum et al. (2017) in the soft ERL setting, and propose a class of novel path consistency learning (PCL) algorithms, called {\em sparse PCL}, for the sparse ERL problem that can work with both on-policy and off-policy data.

Disentangling Dynamics and Content for Control and Planning

no code implementations24 Nov 2017 Ershad Banijamali, Ahmad Khajenezhad, Ali Ghodsi, Mohammad Ghavamzadeh

In this paper, We study the problem of learning a controllable representation for high-dimensional observations of dynamical systems.

Robust Locally-Linear Controllable Embedding

no code implementations15 Oct 2017 Ershad Banijamali, Rui Shu, Mohammad Ghavamzadeh, Hung Bui, Ali Ghodsi

We also propose a principled variational approximation of the embedding posterior that takes the future observation into account, and thus, makes the variational approximation more robust against the noise.

Active Learning for Accurate Estimation of Linear Models

no code implementations ICML 2017 Carlos Riquelme, Mohammad Ghavamzadeh, Alessandro Lazaric

We explore the sequential decision making problem where the goal is to estimate uniformly well a number of linear models, given a shared budget of random contexts independently sampled from a known distribution.

Active Learning Decision Making

Model-Independent Online Learning for Influence Maximization

no code implementations ICML 2017 Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks Lakshmanan, Mark Schmidt

We consider influence maximization (IM) in social networks, which is the problem of maximizing the number of users that become aware of a product by selecting a set of "seed" users to expose the product to.

Bottleneck Conditional Density Estimation

1 code implementation ICML 2017 Rui Shu, Hung H. Bui, Mohammad Ghavamzadeh

We introduce a new framework for training deep generative models for high-dimensional conditional density estimation.

Density Estimation

Conservative Contextual Linear Bandits

no code implementations NeurIPS 2017 Abbas Kazerouni, Mohammad Ghavamzadeh, Yasin Abbasi-Yadkori, Benjamin Van Roy

We prove an upper-bound on the regret of CLUCB and show that it can be decomposed into two terms: 1) an upper-bound for the regret of the standard linear UCB algorithm that grows with the time horizon and 2) a constant (does not grow with the time horizon) term that accounts for the loss of being conservative in order to satisfy the safety constraint.

Decision Making Marketing

Bayesian Reinforcement Learning: A Survey

no code implementations14 Sep 2016 Mohammad Ghavamzadeh, Shie Mannor, Joelle Pineau, Aviv Tamar

The objective of the paper is to provide a comprehensive survey on Bayesian RL algorithms and their theoretical and empirical properties.

Bayesian Inference reinforcement-learning +1

Personalized Advertisement Recommendation: A Ranking Approach to Address the Ubiquitous Click Sparsity Problem

no code implementations6 Mar 2016 Sougata Chaudhuri, Georgios Theocharous, Mohammad Ghavamzadeh

We study the problem of personalized advertisement recommendation (PAR), which consist of a user visiting a system (website) and the system displaying one of $K$ ads to the user.

Graphical Model Sketch

no code implementations9 Feb 2016 Branislav Kveton, Hung Bui, Mohammad Ghavamzadeh, Georgios Theocharous, S. Muthukrishnan, Siqi Sun

Graphical models are a popular approach to modeling structured data but they are unsuitable for high-cardinality variables.

Risk-Constrained Reinforcement Learning with Percentile Risk Criteria

no code implementations5 Dec 2015 Yin-Lam Chow, Mohammad Ghavamzadeh, Lucas Janson, Marco Pavone

In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \emph{risk}, i. e., increased awareness of events of small probability and high consequences.

Decision Making Marketing +2

Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits

no code implementations16 Jul 2015 Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Peter Auer, András Antos

If the variance of the distributions were known, one could design an optimal sampling strategy by collecting a number of independent samples per distribution that is proportional to their variance.

Active Learning Multi-Armed Bandits

Policy Gradient for Coherent Risk Measures

no code implementations NeurIPS 2015 Aviv Tamar, Yin-Lam Chow, Mohammad Ghavamzadeh, Shie Mannor

For static risk measures, our approach is in the spirit of policy gradient algorithms and combines a standard sampling approach with convex programming.

Policy Gradient Methods

Classification-based Approximate Policy Iteration: Experiments and Extended Discussions

no code implementations2 Jul 2014 Amir-Massoud Farahmand, Doina Precup, André M. S. Barreto, Mohammad Ghavamzadeh

We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous.

Classification General Classification

Algorithms for CVaR Optimization in MDPs

no code implementations NeurIPS 2014 Yin-Lam Chow, Mohammad Ghavamzadeh

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in costs in addition to minimizing a standard criterion.

Decision Making

Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs

no code implementations25 Mar 2014 Prashanth L. A., Mohammad Ghavamzadeh

For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize.

Decision Making

Approximate Dynamic Programming Finally Performs Well in the Game of Tetris

no code implementations NeurIPS 2013 Victor Gabillon, Mohammad Ghavamzadeh, Bruno Scherrer

A close look at the literature of this game shows that while ADP algorithms, that have been (almost) entirely based on approximating the value function (value function based), have performed poorly in Tetris, the methods that search directly in the space of policies by learning the policy parameters using an optimization black box, such as the cross entropy (CE) method, have achieved the best reported results.

Actor-Critic Algorithms for Risk-Sensitive MDPs

no code implementations NeurIPS 2013 Prashanth L. A., Mohammad Ghavamzadeh

For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize.

Decision Making

Approximate Modified Policy Iteration

no code implementations14 May 2012 Bruno Scherrer, Victor Gabillon, Mohammad Ghavamzadeh, Matthieu Geist

Modified policy iteration (MPI) is a dynamic programming (DP) algorithm that contains the two celebrated policy and value iteration methods.

General Classification

A Generalized Kernel Approach to Structured Output Learning

no code implementations10 May 2012 Hachem Kadri, Mohammad Ghavamzadeh, Philippe Preux

Finally, we evaluate the performance of our KDE approach using both covariance and conditional covariance kernels on two structured output problems, and compare it to the state-of-the-art kernel-based structured output regression methods.


Multi-Bandit Best Arm Identification

no code implementations NeurIPS 2011 Victor Gabillon, Mohammad Ghavamzadeh, Alessandro Lazaric, Sébastien Bubeck

We first propose an algorithm called Gap-based Exploration (GapE) that focuses on the arms whose mean is close to the mean of the best arm in the same bandit (i. e., small gap).

Speedy Q-Learning

no code implementations NeurIPS 2011 Mohammad Ghavamzadeh, Hilbert J. Kappen, Mohammad G. Azar, Rémi Munos

We introduce a new convergent variant of Q-learning, called speedy Q-learning, to address the problem of slow convergence in the standard form of the Q-learning algorithm.


LSTD with Random Projections

no code implementations NeurIPS 2010 Mohammad Ghavamzadeh, Alessandro Lazaric, Odalric Maillard, Rémi Munos

We provide a thorough theoretical analysis of the LSTD with random projections and derive performance bounds for the resulting algorithm.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.