229 citations · 597 across the 19 of their papers we have counts for
12 papers · 1 filter
Online Self-Weighted Fine-Tuning
Haiquan Wen, Yiwei He, Bei Peng +1
Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Rein…
CURO: Curriculum Learning for Relative Overgeneralization
Lin Shi, Qiyuan Liu, Bei Peng
Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint acti…
Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients
Bozhidar Vasilev, Tarun Gupta, Bei Peng +1
Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenari…
Regularized Softmax Deep Multi-Agent -Learning
Ling Pan, Tabish Rashid, Bei Peng +2
Tackling overestimation in -learning is an important problem that has been extensively studied in single-agent reinforcement learning, but has received comparatively little atte…
RODE: Learning Roles to Decompose Multi-Agent Tasks
Tonghan Wang, Tarun Gupta, Anuj Mahajan +3
Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discove…
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
Tarun Gupta, Anuj Mahajan, Bei Peng +2
VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this ena…
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Tabish Rashid, Gregory Farquhar, Bei Peng +1
QMIX is a popular -learning algorithm for cooperative MARL in the centralised training and decentralised execution paradigm. In order to enable easy decentralisation, QMIX restr…
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng +3
Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge amo…
FACMAC: Factored Multi-Agent Centralised Policy Gradients
Bei Peng, Tabish Rashid, Christian A. Schroeder de Witt +4
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces…
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Sanmit Narvekar, Bei Peng, Matteo Leonetti +3
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over th…
Optimistic Exploration even with a Pessimistic Initialisation
Tabish Rashid, Bei Peng, Wendelin Böhmer +1
Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely…
VIABLE: Fast Adaptation via Backpropagating Learned Loss
Leo Feng, Luisa Zintgraf, Bei Peng +1
In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a re…