Search Results for author:
Found 10 papers, 2 papers with code
Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning
This setting is common in real-world applications, and may be addressed with or without constraints on the cost terms.
Clipped-Objective Policy Gradients for Pessimistic Policy Optimization
To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.
A Risk-Sensitive Approach to Policy Optimization
Without cost constraints, we find that pessimistic risk profiles can be used to reduce cost while improving total reward accumulation.
Triangular Dropout: Variable Network Width without Retraining
After training, the layer can be arbitrarily reduced in width to exchange performance for narrowness.
Meta Arcade: A Configurable Environment Suite for Meta-Learning
Most approaches to deep reinforcement learning (DRL) attempt to solve a single task at a time.
A Risk-Sensitive Policy Gradient Method
Standard deep reinforcement learning (DRL) agents aim to maximize expected reward, considering collected experiences equally in formulating a policy.
Learning a Group-Aware Policy for Robot Navigation
Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments.
Addressing Visual Search in Open and Closed Set Settings
We interpret both detection problems through a probabilistic, Bayesian lens, whereby the objectness maps produced by our method serve as priors in a maximum-a-posteriori approach to the detection step.
On the Complexity of Reconnaissance Blind Chess
This paper provides a complexity analysis for the game of reconnaissance blind chess (RBC), a recently-introduced variant of chess where each player does not know the positions of the opponent's pieces a priori but may reveal a subset of them through chosen, private sensing actions.
Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation.
