An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning
Dec 6, 2021
Speakers
Tianpei Yang
Speaker · 0 followers
About
Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option module can only collect all agent's local experiences for update due to the partial observability of the environment. While in this setting, each agent's experience may be inconsistent with each other, which may cause the inaccuracy and oscillation of the option-value's estimation. Therefore, we propose a novel option learning algorithm, the successor representation option learning to solve it by decoupling the environment dynamics from rewards and learning the option-value under each agent's preference. MAPTF can be easily combined with existing deep RL and MARL approaches, and experimental results show it significantly boosts the performance of existing methods in both discrete and continuous state spaces.Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeli…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Global Filter Networks for Image Classification
Watch later
Yongming Rao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Watch later
Lorenzo Noci, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Watch later
Tim Seyde, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Replay-Guided Adversarial Environment Design
Watch later
Minqi Jiang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Simulated User Studies for Explanation Evaluation
Watch later
Valerie Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%