Search Results for author:
Found 23 papers, 3 papers with code
A Classification View on Meta Learning Bandits
The test regret of the plan in the stochastic and contextual setting scales with $O (\lambda^{-2} C_{\lambda} (\mathbb{M}) \log^2 (MH))$, being $M$ the size of $\mathbb{M}$, $\lambda$ a separation parameter over the bandits, and $C_\lambda (\mathbb{M})$ a novel classification-coefficient that fundamentally links meta learning bandits with classification.
Towards Principled Multi-Agent Task Agnostic Exploration
In this paper, we address this question through a generalization to multiple agents of the problem of maximizing the state distribution entropy.
Reward Compatibility: A Framework for Inverse RL
We provide an original theoretical study of Inverse Reinforcement Learning (IRL) through the lens of reward compatibility, a novel framework to quantify the compatibility of a reward with the given expert's demonstrations.
Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
To achieve this, we bridge AE and MDP homomorphisms, which offer a way to exploit known geometric structures via abstraction.
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied.
How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
We show that the structure offered by Linear MDPs is not sufficient for efficiently estimating the feasible set when the state space is large.
Test-Time Regret Minimization in Meta Reinforcement Learning
Meta reinforcement learning sets a distribution over a set of tasks on which the agent can train at will, then is asked to learn an optimal policy for any test task efficiently.
How to Explore with Belief: State Entropy Maximization in POMDPs
In this paper, we address the problem of entropy maximization over the *true states* with a decision policy conditioned on partial observations *only*.
Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms
In this paper, we introduce a novel notion of feasible reward set capturing the opportunities and limitations of the offline setting and we analyze the complexity of its estimation.
A Theoretical Framework for Partially Observed Reward-States in RLHF
Both of these can be instrumental in speeding up learning and improving alignment.
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
The prior is typically specified as a class of parametric distributions, the design of which can be cumbersome in practice, often resulting in the choice of uninformative priors.
A Tale of Sampling and Estimation in Discounted Reinforcement Learning
In this paper, we present a minimax lower bound on the discounted mean estimation problem that explicitly connects the estimation error with the mixing properties of the Markov process and the discount factor.
Reward-Free Policy Space Compression for Reinforcement Learning
In this paper, we seek for a reward-free compression of the policy space into a finite set of representative policies, such that, given any policy $\pi$, the minimum R\'enyi divergence between the state-action distributions of the representative policies and the state-action distribution of $\pi$ is bounded.
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
In this setting, the agent can take a finite amount of reward-free interactions from a subset of these environments.
The Importance of Non-Markovianity in Maximum State Entropy Exploration
In the maximum state entropy exploration framework, an agent interacts with a reward-free environment to learn a policy that maximizes the entropy of the expected state visitations it is inducing.
Challenging Common Assumptions in Convex Reinforcement Learning
In particular, we show that erroneously optimizing the infinite trials objective in place of the actual finite trials one, as it is usually done, can lead to a significant approximation error.
Unsupervised Reinforcement Learning in Multiple Environments
Along this line, we address the problem of unsupervised reinforcement learning in a class of multiple environments, in which the policy is pre-trained with interactions from the whole class, and then fine-tuned for several tasks in any environment of the class.
Learning to Explore Multiple Environments without Rewards
Along this line, we address the problem of learning to explore a class of multiple reward-free environments with a unique general strategy, which aims to provide a universal initialization to subsequent reinforcement learning problems specified over the same class.
Learning to Explore a Class of Multiple Reward-Free Environments
Along this line, we address the problem of learning to explore a class of multiple reward-free environments with a unique general strategy, which aims to provide a universal initialization to subsequent reinforcement learning problems specified over the same class.
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate
In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy?
A Policy Gradient Method for Task-Agnostic Exploration
In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy?
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies
What is a good exploration strategy for an agent that interacts with an environment in the absence of external rewards?
Configurable Markov Decision Processes
After having introduced our approach and derived some theoretical results, we present the experimental evaluation in two explicative problems to show the benefits of the environment configurability on the performance of the learned policy.
