138 citations · 397 across the 26 of their papers we have counts for
28 papers
Data-Driven Online Model Selection With Regret Guarantees
Aldo Pacchiano, Christoph Dann, Claudio Gentile
We consider model selection for sequential decision making in stochastic environments with bandit feedback, where a meta-learner has at its disposal a pool of base learners, and de…
A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
Christoph Dann, Chen-Yu Wei, Julian Zimmert
Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both the adversarial and the stochastic regimes have received growing attention recently. Ex…
Best of Both Worlds Policy Optimization
Christoph Dann, Chen-Yu Wei, Julian Zimmert
Policy optimization methods are popular reinforcement learning algorithms in practice. Recent works have built theoretical foundation for them by proving regret bounds e…
Pseudonorm Approachability and Applications to Regret Minimization
Christoph Dann, Yishay Mansour, Mehryar Mohri +2
Blackwell's celebrated approachability theory provides a general framework for a variety of learning problems, including regret minimization. However, Blackwell's proof and implici…
Learning in POMDPs is Sample-Efficient with Hindsight Observability
Jonathan N. Lee, Alekh Agarwal, Christoph Dann +1
POMDPs capture a broad class of decision making problems, but hardness results suggest that learning is intractable even in simple settings due to the inherent partial observabilit…
A Unified Algorithm for Stochastic Path Problems
Christoph Dann, Chen-Yu Wei, Julian Zimmert
We study reinforcement learning in stochastic path (SP) problems. The goal in these problems is to maximize the expected sum of rewards until the agent reaches a terminal state. We…
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning
Christoph Dann, Mehryar Mohri, Tong Zhang +1
Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior s…
Best of Both Worlds Model Selection
Aldo Pacchiano, Christoph Dann, Claudio Gentile
We study the problem of model selection in bandit scenarios in the presence of nested policy classes, with the goal of obtaining simultaneous adversarial and stochastic ("best of b…
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Christoph Dann, Yishay Mansour, Mehryar Mohri +2
Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian noise fail to explore efficiently in some reinforcement learning tasks and yet, they perform well in many o…
Leveraging Initial Hints for Free in Stochastic Linear Bandits
Ashok Cutkosky, Chris Dann, Abhimanyu Das +2
We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a n…
Same Cause; Different Effects in the Brain
Mariya Toneva, Jennifer Williams, Anand Bollu +2
To study information processing in the brain, neuroscientists manipulate experimental stimuli while recording participant brain activity. They can then use encoding models to find…
A Model Selection Approach for Corruption Robust Reinforcement Learning
Chen-Yu Wei, Christoph Dann, Julian Zimmert
We develop a model selection approach to tackle reinforcement learning with adversarial corruption in both transition and reward. For finite-horizon tabular MDPs, without prior kno…
Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Christoph Dann, Teodor V. Marinov, Mehryar Mohri +1
We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative de…
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Christoph Dann, Yishay Mansour, Mehryar Mohri +2
There have been many recent advances on provably efficient Reinforcement Learning (RL) in problems with rich observation spaces. However, all these works share a strong realizabili…
Neural Active Learning with Performance Guarantees
Pranjal Awasthi, Christoph Dann, Claudio Gentile +2
We investigate the problem of active learning in the streaming setting in non-parametric regimes, where the labels are stochastically generated from a class of functions on which w…
Regret Bound Balancing and Elimination for Model Selection in Bandits and RL
Aldo Pacchiano, Christoph Dann, Claudio Gentile +1
We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge o…
Reinforcement Learning with Feedback Graphs
Christoph Dann, Yishay Mansour, Mehryar Mohri +2
We study episodic reinforcement learning in Markov decision processes when the agent receives additional feedback per step in the form of several transition observations. Such addi…
Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy
Ramtin Keramati, Christoph Dann, Alex Tamkin +1
While maximizing expected return is the goal in most reinforcement learning approaches, risk-sensitive objectives such as conditional value at risk (CVaR) are more suitable for man…
Policy Certificates: Towards Accountable Reinforcement Learning
Christoph Dann, Lihong Li, Wei Wei +1
The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration. Existing algorithms provide little information about the quality…
On Oracle-Efficient PAC RL with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy +3
We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministi…
Decoupling Learning Rules from Representations
Philip S. Thomas, Christoph Dann, Emma Brunskill
In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression…
Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
Christoph Dann, Tor Lattimore, Emma Brunskill
Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for th…
Sample Efficient Policy Search for Optimal Stopping Domains
Karan Goel, Christoph Dann, Emma Brunskill
Optimal stopping problems consider the question of deciding when to stop an observation-generating process in order to maximize a return. We examine the problem of simultaneously l…
Memory Lens: How Much Memory Does an Agent Use?
Christoph Dann, Katja Hofmann, Sebastian Nowozin
We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information b…