Search Results for author:
Found 9 papers, 7 papers with code
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers.
Orchestrated Value Mapping for Reinforcement Learning
We present a general convergent class of reinforcement learning algorithms that is founded on two distinct principles: (1) mapping value estimates to a different space using arbitrary functions from a broad class, and (2) linearly decomposing the reward signal into multiple channels.
Learning to Represent Action Values as a Hypergraph on the Action Vertices
To test this, we set forth the action hypergraph networks framework -- a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias.
A neural network oracle for quantum nonlocality problems in networks
As such, the neural network acts as an oracle, demonstrating that a behavior is classical if it can be learned.
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to study each effect in isolation.
Exploring Restart Distributions
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution.
Time Limits in Reinforcement Learning
In case (ii), the time limits are not part of the environment and are only used to facilitate learning.
Action Branching Architectures for Deep Reinforcement Learning
This approach achieves a linear increase of the number of network outputs with the number of degrees of freedom by allowing a level of independence for each individual action dimension.
Multiplayer Games for Learning Multirobot Coordination Algorithms
This ability, if learned as a set of distributed multirobot coordination strategies, can enable programming large groups of robots to collaborate towards complex coordination objectives in a way similar to humans.
