Related papers: Maximum Entropy Population-Based Training for Zero…

Collaborating with humans requires rapidly adapting to their individual strengths, weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement learning techniques, such as self-play (SP) or population play (PP),…

Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents,…

Recent advances in reinforcement learning have demonstrated its ability to solve hard agent-environment interaction tasks on a super-human level. However, the application of reinforcement learning methods to practical and real-world tasks…

A major challenge for deep reinforcement learning (DRL) agents is to collaborate with novel partners that were not encountered by them during the training phase. This is specifically worsened by an increased variance in action responses…

Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discriminant information, a single network has difficulty learning…

Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based…

Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent.…

Zero-shot human-AI coordination holds the promise of collaborating with humans without human data. Prevailing methods try to train the ego agent with a population of partners via self-play. However, these methods suffer from two problems:…

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…

Maximum entropy principle (MEP) offers an effective and unbiased approach to inferring unknown probability distributions when faced with incomplete information, while neural networks provide the flexibility to learn complex distributions…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

Training populations of agents has demonstrated great promise in Reinforcement Learning for stabilizing training, improving exploration and asymptotic performance, and generating a diverse set of solutions. However, population-based…

There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play…

Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving…

Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expertise at the world's oldest board games and many classic video…

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In…

We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating with each other in the game. It is difficult to train powerful agents that can defeat top human players in AMP…

Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittleness of RL algorithms to core hyperparameters and network…