arXiv research

New method for optimistic planning in MDPs using regularization.

We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is …

Proposes H-UCRL for efficient model-based RL with sublinear regret.

The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.

New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.

We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played. While being a natural extension of the classical bandit problem that arises in many real-world settin…

Optimistic algorithm reduces regret in non-stationary linear MDPs.

In many cases an intelligent agent may want to learn how to mimic a single observed demonstrated trajectory. In this work we consider how to perform such procedural learning from observation, which could help to enable agents to better use the enormous set of video data on observation sequences. Our approach exploits t…

New algorithm explores reinforcement learning with noisy data.

RandQL is a new model-free algorithm for MDPs with a novel learning rate randomization approach.

This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.

Bayesian classifier improves robustness with optimistic score ratio.

We show that the optimistic limits of the colored Jones polynomials of the hyperbolic knots coincide with the optimistic limits of the Kashaev invariants modulo $4π^2$.

Proposes Optimistic Pessimistically Initialised Q-Learning (OPIQ) for better exploration in RL.

We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value f…

The optimistic limit is the mathematical formulation of the classical limit which is a physical method to expect the actual limit by using saddle point method of certain potential function. The original optimistic limit of the Kashaev invariant was formulated by Yokota, and a modified formulation was suggested by the a…

Optimistic estimate predicts best fitting performance of nonlinear models.

New algorithm reduces regret in sequential decision-making problems.

Optimistic NPG improves policy optimization in online RL with efficient sample complexity.

Characterizes concept classes for optimistic online learning.

We show how to take any two parameter-free online learning algorithms with different regret guarantees and obtain a single algorithm whose regret is the minimum of the two base algorithms. Our method is embarrassingly simple: just add the iterates. This trick can generate efficient algorithms that adapt to many norms s…

New algorithms reduce forecasting errors by leveraging optimistic learning and hinting.

New RL method explores environments without rewards, achieving efficient policy generation.

Omega method mitigates noise in stochastic game optimization.

New method minimizes regret in AMDP with high probability.

Unified framework for model- and value-optimistic reinforcement learning.

New algorithm learns POMDPs without computational oracles.

It is well known that in stochastic multi-armed bandits (MAB), the sample mean of an arm is typically not an unbiased estimator of its true mean. In this paper, we decouple three different sources of this selection bias: adaptive \emph{sampling} of arms, adaptive \emph{stopping} of the experiment, and adaptively \emph{…

Efficiently solves exploration-exploitation in LQR using Lagrangian relaxation.

Logarithmic regret achieved in Q-learning with positive gap.

A fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions. Frequently, these nominal distributions are themselves estimated from data, which makes them susceptible to estimation errors. We thus propose to replace each…

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

Optimistic method adapted for faster convex-concave min-max problems.

This paper develops a model of reference-dependent assessment of subjective beliefs in which loss-averse people optimally choose the expectation as the reference point to balance the current felicity from the optimistic anticipation and the future disappointment from the realisation. The choice of over-optimism or over…

Optimistic PPO variant solves linear MDPs with improved regret bound.

Study optimizes linear regression analysis for high-dimensional settings.

Novel approach to universal online learning for bounded losses, closing open problems.

We address the issue of limit cycling behavior in training Generative Adversarial Networks and propose the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs. Recent theoretical results have shown that optimistic mirror decent (OMD) can enjoy faster regret rates in the context of zero-sum games. WGANs …

Solves open problem on universally consistent online learning with unbounded losses.

Optimistic bounds for multi-output learning using self-bounding Lipschitz condition.

In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and $TD(λ)$ methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.

Accelerates policy optimization in RL with optimistic and adaptive updates.

Unified framework for model-based RL with sample complexity guarantees.

Optimistic pricing algorithm handles online dynamic pricing with censored demand.

Yokota suggested an optimistic limit method of the Kashaev invariants of hyperbolic knots and showed it determines the complex volumes of the knots. His method is very effective and gives almost combinatorial method of calculating the complex volumes. However, to describe the triangulation of the knot complement, he re…

New algorithms solve linear bandits in high dimensions efficiently.

Safe linear bandits over unknown polytopes avoid safety violations and suboptimal actions.

Optimistic RL algorithms are simplified for deep RL with competitive performance.