Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning
read the original abstract
Parameter sharing, where each agent independently learns a policy with fully shared parameters between all policies, is a popular baseline method for multi-agent deep reinforcement learning. Unfortunately, since all agents share the same policy network, they cannot learn different policies or tasks. This issue has been circumvented experimentally by adding an agent-specific indicator signal to observations, which we term "agent indication". Agent indication is limited, however, in that without modification it does not allow parameter sharing to be applied to environments where the action spaces and/or observation spaces are heterogeneous. This work formalizes the notion of agent indication and proves that it enables convergence to optimal policies for the first time. Next, we formally introduce methods to extend parameter sharing to learning in heterogeneous observation and action spaces, and prove that these methods allow for convergence to optimal policies. Finally, we experimentally confirm that the methods we introduce function empirically, and conduct a wide array of experiments studying the empirical efficacy of many different agent indication schemes for image based observation spaces.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
Events trigger on-the-fly LoRA module generation via hypernetworks over a shared team policy in MARL, paired with a Neural Manifold Diversity metric, enabling sequential role reassignment while preserving reward maximization.
-
Randomness is sometimes necessary for coordination
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-sh...
-
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
-
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
Proposes an event-triggered MARL framework with Neural Manifold Diversity and event-based hypernetworks to enable dynamic, agent-agnostic behavioral transitions while preserving reward maximization.
-
DelAC: A Multi-agent Reinforcement Learning of Team-Symmetric Stochastic Games
Team-symmetric games always have team-symmetric Nash equilibria solvable via linear complementarity problems, and the DelAC actor-critic MARL algorithm outperforms existing methods in simulations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.