55 citations · 66 across the 3 of their papers we have counts for
7 papers · 1 filter
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
Michael Chang, Sidhant Kaushik, Sergey Levine +1
Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choos…
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
Michael Chang, Sidhant Kaushik, S. Matthew Weinberg +2
This paper seeks to establish a framework for directing a society of simple, specialized, self-interested agents to solve what traditionally are posed as monolithic single-agent se…
Entity Abstraction in Visual Model-Based Reinforcement Learning
Rishi Veerapaneni, John D. Co-Reyes, Michael Chang +5
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit i…
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
Xue Bin Peng, Michael Chang, Grace Zhang +2
Humans are able to perform a myriad of sophisticated tasks by drawing upon skills acquired through prior experience. For autonomous agents to have this capability, they must be abl…
Automatically Composing Representation Transformations as a Means for Generalization
Michael B. Chang, Abhishek Gupta, Sergey Levine +1
A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a se…
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Sjoerd van Steenkiste, Michael Chang, Klaus Greff +1
Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to inf…