Search Results for author:
Found 23 papers, 4 papers with code
Simple Ingredients for Offline Reinforcement Learning
Offline reinforcement learning algorithms have proven effective on datasets highly connected to the target downstream task.
Towards Instance-Optimality in Online PAC Reinforcement Learning
In this paper, we propose the first instance-dependent lower bound on the sample complexity required for the PAC identification of a near-optimal policy in any tabular episodic MDP.
Active Coverage for PAC Reinforcement Learning
In particular, we obtain a simple algorithm for PAC reward-free exploration with an instance-dependent sample complexity that, in certain MDPs which are "easy to explore", is lower than the minimax one.
Layered State Discovery for Incremental Autonomous Exploration
We leverage these results to design Layered Autonomous Exploration (LAE), a novel algorithm for AX that attains a sample complexity of $\tilde{\mathcal{O}}(LS^{\rightarrow}_{L(1+\epsilon)}\Gamma_{L(1+\epsilon)} A \ln^{12}(S^{\rightarrow}_{L(1+\epsilon)})/\epsilon^2)$, where $S^{\rightarrow}_{L(1+\epsilon)}$ is the number of states that are incrementally $L(1+\epsilon)$-controllable, $A$ is the number of actions, and $\Gamma_{L(1+\epsilon)}$ is the branching factor of the transitions over such states.
On the Complexity of Representation Learning in Contextual Linear Bandits
In contextual linear bandits, the reward function is assumed to be a linear combination of an unknown reward vector and a given embedding of context-arm pairs.
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
We study the problem of representation learning in stochastic contextual linear bandits.
Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
We also initiate the study of learning $\epsilon$-optimal policies without access to a generative model (i. e., the so-called best-policy identification problem), and show that sample-efficient learning is impossible in general.
Optimistic PAC Reinforcement Learning: the Instance-Dependent View
Optimistic algorithms have been extensively studied for regret minimization in episodic tabular MDPs, both from a minimax and an instance-dependent view.
On Elimination Strategies for Bandit Fixed-Confidence Identification
Elimination algorithms for bandit identification, which prune the plausible correct answers sequentially until only one remains, are computationally convenient since they reduce the problem size over time.
Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs
In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$.
Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification
In this work, we first derive a tractable lower bound on the sample complexity of any $\delta$-correct algorithm for the general Top-m identification problem.
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure.
A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs
We derive a novel asymptotic problem-dependent lower-bound for regret minimization in finite-horizon tabular Markov Decision Processes (MDPs).
Meta-Reinforcement Learning by Tracking Task Non-stationarity
At test time, TRIO tracks the evolution of the latent parameters online, hence reducing the uncertainty over future tasks and obtaining fast adaptation through the meta-learned policy.
Leveraging Good Representations in Linear Contextual Bandits
We show that the regret is indeed never worse than the regret obtained by running LinUCB on the best representation (up to a $\ln M$ factor).
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits
Finally, we remove forced exploration and build on confidence intervals of the optimization problem to encourage a minimum level of exploration that is better adapted to the problem structure.
Sequential Transfer in Reinforcement Learning with a Generative Model
We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones.
A Novel Confidence-Based Algorithm for Structured Bandits
We study finite-armed stochastic bandits where the rewards of each arm might be correlated to those of other arms.
Gradient-Aware Model-based Policy Search
In this paper, we introduce a novel model-based policy search approach that exploits the knowledge of the current agent policy to learn an approximate transition model, focusing on the portions of the environment that are most relevant for policy improvement.
Feature Selection via Mutual Information: New Theoretical Insights
Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables.
Transfer of Value Functions via Variational Methods
We consider the problem of transferring value functions in reinforcement learning.
Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes
What policy should be employed in a Markov decision process with uncertain parameters?
Importance Weighted Transfer of Samples in Reinforcement Learning
In the proposed approach, all the samples are transferred and used by a batch RL algorithm to solve the target task, but their contribution to the learning process is proportional to their importance weight.
