Reinforcement Learning
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning Harley Wiltzer Mila-Québec AI Institute McGill University Marc G. Bellemare
In addition, we build a superiority-based DRL algorithm.
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination Xihuai Wang
The significant difference between the deployment-time partners' distribution and the training partners' distribution determined by the
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Figure 1: Complex decision problems that require a good understanding of the environment's
Simplifying Constraint Inference with Inverse Reinforcement Learning
The field of inverse constrained RL, which seeks to infer constraints from expert data, is a promising step in this direction.
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
These challenges are partially due to a lack of structure or inductive bias in the neural networks typically used in learning the policy. One such form of structure that is commonly observed in multi-agent scenarios is symmetry.