Search Results for author:
Found 27 papers, 8 papers with code
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts.
Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria
By directly comparing active equilibria to Nash equilibria in these examples, we find that active equilibria find more effective solutions than Nash equilibria, concluding that an active equilibrium is the desired solution for multiagent learning settings.
Influencing Long-Term Behavior in Multiagent Reinforcement Learning
An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other agents and influence the evolution of future policies towards desirable behavior for its own benefit.
Continual Learning In Environments With Polynomial Mixing Times
The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios.
Context-Specific Representation Abstraction for Deep Option Learning
Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration.
Towards Continual Reinforcement Learning: A Review and Perspectives
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL.
Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm.
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents.
Deep RL With Information Constrained Policies: Generalization in Continuous Control
We focus on the model-free reinforcement learning (RL) setting and formalize our approach in terms of an information-theoretic constraint on the complexity of learned policies.
A Study of Compositional Generalization in Neural Models
One difficulty in the development of such models is the lack of benchmarks with clear compositional and relational task structure on which to systematically evaluate them.
Efficient Black-Box Planning Using Macro-Actions with Focused Effects
Focused macros dramatically improve black-box planning efficiency across a wide range of planning domains, sometimes beating even state-of-the-art planners with access to a full domain model.
Coagent Networks Revisited
Coagent networks formalize the concept of arbitrary networks of stochastic agents that collaborate to take actions in a reinforcement learning environment.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
On the Role of Weight Sharing During Deep Option Learning
In this work we note that while this key assumption of the policy gradient theorems of option-critic holds in the tabular case, it is always violated in practice for the deep function approximation setting.
Hierarchical Average Reward Policy Gradient Algorithms
Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions.
CAPACITY-LIMITED REINFORCEMENT LEARNING: APPLICATIONS IN DEEP ACTOR-CRITIC METHODS FOR CONTINUOUS CONTROL
We formalize this type of bounded rationality in terms of an information-theoretic constraint on the complexity of policies that agents seek to learn.
Recursive Routing Networks: Learning to Compose Modules for Language Understanding
The model jointly optimizes the parameters of the functions and the meta-learner{'}s policy for routing inputs through those functions.
Routing Networks and the Challenges of Modular and Compositional Computation
Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality.
Continual Learning with Self-Organizing Maps
Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones.
Learning Hierarchical Teaching Policies for Cooperative Agents
Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers.
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples.
Learning Abstract Options
Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning.
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences.
Learning to Teach in Cooperative Multiagent Reinforcement Learning
The problem of teaching to improve agent learning has been investigated by prior works, but these approaches make assumptions that prevent application of teaching to general multiagent problems, or require domain expertise for problems they can apply to.
Scalable Recollections for Continual Lifelong Learning
Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings.
Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning
A routing network is a kind of self-organizing neural network consisting of two components: a router and a set of one or more function blocks.
Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning
We demonstrate our approach on a Twitter domain sentiment analysis task with sequential knowledge transfer from four related tasks.
