Search Results for author:
Found 30 papers, 13 papers with code
Learning in Factored Domains with Information-Constrained Visual Representations
This raises the question of how humans learn to efficiently represent visual information in a manner useful for learning tasks.
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.
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.
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability.
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.
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making.
Ranked #1 on
Commonsense Reasoning for RL
on commonsense-rl
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches
We introduce a number of RL agents that combine the sequential context with a dynamic graph representation of their beliefs of the world and commonsense knowledge from ConceptNet in different ways.
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.
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.
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.
Hybrid Reinforcement Learning with Expert State Sequences
The empirical results show that (1) the agents are able to leverage state expert sequences to learn faster than pure reinforcement learning baselines, (2) our tensor-based action inference model is advantageous compared to standard deep neural networks in inferring expert actions, and (3) the hybrid policy optimization objective is robust against noise in expert state sequences.
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.
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.
Diverse Few-Shot Text Classification with Multiple Metrics
We study few-shot learning in natural language domains.
Dialog-based Interactive Image Retrieval
Experiments on both simulated and real-world data show that 1) our proposed learning framework achieves better accuracy than other supervised and reinforcement learning baselines and 2) user feedback based on natural language rather than pre-specified attributes leads to more effective retrieval results, and a more natural and expressive communication interface.
Faster Reinforcement Learning with Expert State Sequences
In this paper, we consider a realistic and more difficult sce- nario where a reinforcement learning agent only has access to the state sequences of an expert, while the expert actions are not available.
The Eigenoption-Critic Framework
Eigenoptions (EOs) have been recently introduced as a promising idea for generating a diverse set of options through the graph Laplacian, having been shown to allow efficient exploration.
Efficient Exploration
Hierarchical Reinforcement Learning
+1
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer.
Ranked #1 on
Open-Domain Question Answering
on Quasar
Eigenoption Discovery through the Deep Successor Representation
Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning.
R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.
Ranked #4 on
Open-Domain Question Answering
on Quasar
Robust Task Clustering for Deep Many-Task Learning
We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario.
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.
Ranked #1 on
Dialogue Generation
on Ubuntu Dialogue (Activity)
Hierarchical Memory Networks
In this paper, we explore a form of hierarchical memory network, which can be considered as a hybrid between hard and soft attention memory networks.
Selecting Near-Optimal Learners via Incremental Data Allocation
We study a novel machine learning (ML) problem setting of sequentially allocating small subsets of training data amongst a large set of classifiers.
Analysis of Watson's Strategies for Playing Jeopardy!
After giving a detailed description of each of our game-strategy algorithms, we then focus in particular on validating the accuracy of the simulators predictions, and documenting performance improvements using our methods.
