Search Results for author:
Found 60 papers, 28 papers with code
Never Explore Repeatedly in Multi-Agent Reinforcement Learning
In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse
Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task.
Learning to Solve Tasks with Exploring Prior Behaviours
Our method can endow agents with the ability to explore and acquire the required prior behaviours and then connect to the task-specific behaviours in the demonstration to solve sparse-reward tasks without requiring additional demonstration of the prior behaviours.
Symmetry-Aware Robot Design with Structured Subgroups
Robot design aims at learning to create robots that can be easily controlled and perform tasks efficiently.
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
We find a return-based uncertainty quantification for IDAQ that performs effectively.
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
In this paper, we study out-of-distribution (OOD) generalization of offline GCRL both theoretically and empirically to identify factors that are important.
The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning
Self-supervised methods have become crucial for advancing deep learning by leveraging data itself to reduce the need for expensive annotations.
A Survey on Transformers in Reinforcement Learning
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings.
Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery
We show that such lossless primitives can drastically improve the performance of hierarchical policies.
Non-Linear Coordination Graphs
Value decomposition multi-agent reinforcement learning methods learn the global value function as a mixing of each agent's individual utility functions.
Low-Rank Modular Reinforcement Learning via Muscle Synergy
Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator.
CUP: Critic-Guided Policy Reuse
The ability to reuse previous policies is an important aspect of human intelligence.
Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework
Decentralized execution is one core demand in cooperative multi-agent reinforcement learning (MARL).
Multi-agent Reinforcement Learning
Policy Gradient Methods
+2
On the Role of Discount Factor in Offline Reinforcement Learning
The discount factor, $\gamma$, plays a vital role in improving online RL sample efficiency and estimation accuracy, but the role of the discount factor in offline RL is not well explored.
RORL: Robust Offline Reinforcement Learning via Conservative Smoothing
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks.
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions.
Multi-Agent Policy Transfer via Task Relationship Modeling
We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks.
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm.
MOORe: Model-based Offline-to-Online Reinforcement Learning
With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online.
Self-Organized Polynomial-Time Coordination Graphs
However, one critical challenge in this paradigm is the complexity of greedy action selection with respect to the factorized values.
Model-Based Reinforcement Learning via Imagination with Derived Memory
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+1
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration
Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems.
Offline Reinforcement Learning with Value-based Episodic Memory
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data.
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning tasks put a high demand on the volume of training samples.
Offline Reinforcement Learning with Reverse Model-based Imagination
These reverse imaginations provide informed data augmentation for model-free policy learning and enable conservative generalization beyond the offline dataset.
On the Estimation Bias in Double Q-Learning
Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation.
Learning Homophilic Incentives in Sequential Social Dilemmas
Promoting cooperation among self-interested agents is a long-standing and interdisciplinary problem, but receives less attention in multi-agent reinforcement learning (MARL).
Safe Opponent-Exploitation Subgame Refinement
Search algorithms have been playing a vital role in the success of superhuman AI in both perfect information and imperfect information games.
Learning the Representation of Behavior Styles with Imitation Learning
Imitation learning is one of the methods for reproducing expert demonstrations adaptively by learning a mapping between observations and actions.
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates
During long-time observations, agents can build \textit{awareness} for teammates to alleviate the problem of partial observability.
Context-Aware Sparse Deep Coordination Graphs
Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning.
Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Active Hierarchical Exploration with Stable Subgoal Representation Learning
Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards.
Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL
We propose a novel learning framework to encourage homophilic incentives and show that it achieves stable cooperation in both SSDs of public goods and tragedy of the commons.
Generalizable Episodic Memory for Deep Reinforcement Learning
Episodic memory-based methods can rapidly latch onto past successful strategies by a non-parametric memory and improve sample efficiency of traditional reinforcement learning.
DOP: Off-Policy Multi-Agent Decomposed Policy Gradients
In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP).
Learning Subgoal Representations with Slow Dynamics
In goal-conditioned Hierarchical Reinforcement Learning (HRL), a high-level policy periodically sets subgoals for a low-level policy, and the low-level policy is trained to reach those subgoals.
Intrinsically Guided Exploration in Meta Reinforcement Learning
Deep reinforcement learning algorithms generally require large amounts of data to solve a single task.
Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning
We introduce the Fever Basketball game, a novel reinforcement learning environment where agents are trained to play basketball game.
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
It maximizes the mutual information between imaginary and real trajectories so that the policy improvement learned from imaginary trajectories can be easily generalized to real trajectories.
Model-based Reinforcement Learning
reinforcement-learning
+1
RODE: Learning Roles to Decompose Multi-Agent Tasks
Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces.
Towards Understanding Linear Value Decomposition in Cooperative Multi-Agent Q-Learning
Value decomposition is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings.
QPLEX: Duplex Dueling Multi-Agent Q-Learning
This paper presents a novel MARL approach, called duPLEX dueling multi-agent Q-learning (QPLEX), which takes a duplex dueling network architecture to factorize the joint value function.
Off-Policy Multi-Agent Decomposed Policy Gradients
In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP).
SOAC: The Soft Option Actor-Critic Architecture
In these tasks, our approach learns a diverse set of options, each of whose state-action space has strong coherence.
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks.
Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization
Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions.
Episodic Reinforcement Learning with Associative Memory
Sample efficiency has been one of the major challenges for deep reinforcement learning.
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA).
Multiagent Systems
Influence-Based Multi-Agent Exploration
We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents.
Learning Nearly Decomposable Value Functions Via Communication Minimization
Recently, value function factorization learning emerges as a promising way to address these challenges in collaborative multi-agent systems.
Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
In addition, we also theoretically prove that optimizing low-level skills with this auxiliary reward will increase the task return for the joint policy.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Object-Oriented Model Learning through Multi-Level Abstraction
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability.
Object-Oriented Dynamics Learning through Multi-Level Abstraction
We also design a spatial-temporal relational reasoning mechanism for MAOP to support instance-level dynamics learning and handle partial observability.
Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games
Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees.
Towards Efficient Detection and Optimal Response against Sophisticated Opponents
This paper proposes a novel approach called Bayes-ToMoP which can efficiently detect the strategy of opponents using either stationary or higher-level reasoning strategies.
Multiagent Systems
Context-Aware Policy Reuse
Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks.
Object-Oriented Dynamics Predictor
Generalization has been one of the major challenges for learning dynamics models in model-based reinforcement learning.
An Optimal Online Method of Selecting Source Policies for Reinforcement Learning
In this paper, we develop an optimal online method to select source policies for reinforcement learning.
Fairness in Multi-Agent Sequential Decision-Making
We develop a simple linear programming approach and a more scalable game-theoretic approach for computing an optimal fairness policy.
