Search Results for author:
Found 42 papers, 12 papers with code
Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging
Averaging predictions from 10 models reduced variability by nearly 70% (mean coefficient of variation from 0. 543 to 0. 169, t-test 15. 96, p-value < 0. 0001).
Faster Deep Reinforcement Learning with Slower Online Network
In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network.
Lipschitz Continuity in Model-based Reinforcement Learning
We go on to prove an error bound for the value-function estimate arising from Lipschitz models and show that the estimated value function is itself Lipschitz.
Model-based Reinforcement Learning
reinforcement-learning
+1
An Object-Oriented Representation for Efficient Reinforcement Learning
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces.
Lipschitz Lifelong Reinforcement Learning
We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks.
Near Optimal Behavior via Approximate State Abstraction
The combinatorial explosion that plagues planning and reinforcement learning (RL) algorithms can be moderated using state abstraction.
Learning Approximate Stochastic Transition Models
We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions.
Model-based Reinforcement Learning
reinforcement-learning
+1
Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex
AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex.
Learning State Abstractions for Transfer in Continuous Control
In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks.
Tiered Reward Functions: Specifying and Fast Learning of Desired Behavior
Reinforcement-learning agents seek to maximize a reward signal through environmental interactions.
An Alternative Softmax Operator for Reinforcement Learning
A softmax operator applied to a set of values acts somewhat like the maximization function and somewhat like an average.
Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning
Learning a generative model is a key component of model-based reinforcement learning.
Model-based Reinforcement Learning
reinforcement-learning
+1
Modeling Latent Attention Within Neural Networks
Deep neural networks are able to solve tasks across a variety of domains and modalities of data.
Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting
Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution.
Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks.
Environment-Independent Task Specifications via GLTL
We propose a new task-specification language for Markov decision processes that is designed to be an improvement over reward functions by being environment independent.
Interactive Learning from Policy-Dependent Human Feedback
This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback.
Graphical Models for Game Theory
The interpretation is that the payoff to player i is determined entirely by the actions of player i and his neighbors in the graph, and thus the payoff matrix to player i is indexed only by these players.
Incremental Pruning: A Simple, Fast, Exact Method for Partially Observable Markov Decision Processes
Most exact algorithms for general partially observable Markov decision processes (POMDPs) use a form of dynamic programming in which a piecewise-linear and convex representation of one value function is transformed into another.
Transfer with Model Features in Reinforcement Learning
Further, we present a Successor Feature model which shows that learning Successor Features is equivalent to learning a Model-Reduction.
Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes.
Model-based Reinforcement Learning
reinforcement-learning
+1
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model.
Multi-resolution Exploration in Continuous Spaces
The essence of exploration is acting to try to decrease uncertainty.
Online Linear Regression and Its Application to Model-Based Reinforcement Learning
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting.
Theory of Minds: Understanding Behavior in Groups Through Inverse Planning
This representation is grounded in the formalism of stochastic games and multi-agent reinforcement learning.
Successor Features Combine Elements of Model-Free and Model-based Reinforcement Learning
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs.
Deep Reinforcement Learning from Policy-Dependent Human Feedback
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users.
Interactive Learning of Environment Dynamics for Sequential Tasks
In order for robots and other artificial agents to efficiently learn to perform useful tasks defined by an end user, they must understand not only the goals of those tasks, but also the structure and dynamics of that user's environment.
Stackelberg Punishment and Bully-Proofing Autonomous Vehicles
This idea generalizes the concept of a Stackelberg equilibrium.
Deep Radial-Basis Value Functions for Continuous Control
We show that the maximum action-value with respect to a deep RBVF can be approximated easily and accurately.
The Efficiency of Human Cognition Reflects Planned Information Processing
Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions.
Context-Driven Satirical News Generation
While mysterious, humor likely hinges on an interplay of entities, their relationships, and cultural connotations.
Towards Sample Efficient Agents through Algorithmic Alignment
We demonstrate the potential of graph neural network in supporting sample efficient learning by showing that Deep Graph Value Network can outperform unstructured baselines by a large margin in solving the Markov Decision Process (MDP).
People construct simplified mental representations to plan
We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting.
Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program
The advances in artificial intelligence enabled by deep learning architectures are undeniable.
Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback
We propose a variant of COACH, episodic COACH (E-COACH), which we prove converges for all three types.
Bad-Policy Density: A Measure of Reinforcement Learning Hardness
We address this question by proposing a simple measure of reinforcement-learning hardness called the bad-policy density.
On the Expressivity of Markov Reward
We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists.
Designing Rewards for Fast Learning
To solve this optimization problem, we propose a linear-programming based algorithm that efficiently finds a reward function that maximizes action gap and minimizes subjective discount.
Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
Reward-Predictive Clustering
Recent advances in reinforcement-learning research have demonstrated impressive results in building algorithms that can out-perform humans in complex tasks.
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
