Search Results for author:
Found 10 papers, 3 papers with code
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct Preference Optimization (DPO).
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
In a large-scale cluster, the novel architecture of SRL leads to up to 3. 7x speedup compared to the design choices adopted by the existing libraries.
Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
Despite all the advantages, we revisit these two principles and show that in certain scenarios, e. g., environments with a highly multi-modal reward landscape, value decomposition, and parameter sharing can be problematic and lead to undesired outcomes.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization
We present Reward-Switching Policy Optimization (RSPO), a paradigm to discover diverse strategies in complex RL environments by iteratively finding novel policies that are both locally optimal and sufficiently different from existing ones.
How to "DODGE" Complex Software Analytics?
Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i. e., automatic tools that find good settings for a learner's control parameters.
500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow)
Deep learners utilizes extensive computational power and can take a long time to train-- making it difficult to widely validate and repeat and improve their results.
Easy over Hard: A Case Study on Deep Learning
While deep learning is an exciting new technique, the benefits of this method need to be assessed with respect to its computational cost.
Revisiting Unsupervised Learning for Defect Prediction
(1) There is much variability in the efficacy of the Yang et al. predictors so even with their approach, some supervised data is required to prune weaker predictors away.
Why is Differential Evolution Better than Grid Search for Tuning Defect Predictors?
In software analytics, at least for defect prediction, several methods, like grid search and differential evolution (DE), have been proposed to learn these parameters, which has been proved to be able to improve the performance scores of learners.
What is Wrong with Topic Modeling? (and How to Fix it Using Search-based Software Engineering)
When run on different datasets, LDA suffers from "order effects" i. e. different topics are generated if the order of training data is shuffled.
