Search Results for author:
Found 5 papers, 0 papers with code
FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning
Explicit communication among humans is key to coordinating and learning.
Towards True Lossless Sparse Communication in Multi-Agent Systems
We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity.
Probe-Based Interventions for Modifying Agent Behavior
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified.
Interpretable Learned Emergent Communication for Human-Agent Teams
In human-agent teams tested in benchmark environments, where agents have been modeled using the Enforcers, we find that a prototype-based method produces meaningful discrete tokens that enable human partners to learn agent communication faster and better than a one-hot baseline.
