Agents
Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus
This paper considers offline multi-agent reinforcement learning.
Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus
This paper considers offline multi-agent reinforcement learning.
Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization Appendix
So in this paper, we use the scalar states as well as Lidar-like measures as the observation for each agent, which also improves the efficiency of our simulator.
Information is Power: Intrinsic Control via Information Capture
Figure 1: The agent uses a latent state space model to represent beliefs about the world, including dynamic objects like the goat. The blue window represents the agent's field-of-view, which defines the extent of the
48adb34f7ee39177c4c23a8e4253a492-Paper-Conference.pdf
AIs can surpass human performance by a large margin.
Learning in Congestion Games with Bandit Feedback
To help address these issues, a natural approach is to consider games with special structures. In this paper, we focus on congestion games.