Research map / Multi-agent systems and games / Games and equilibria
Learning to Collaborate in Markov Decision Processes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use OFTRL with double recency bias and a history horizon tuned to the policy-change rate | Agent A₁ in the two-agent MDP · Two-agent MDP with ρ₂ = O(T⁻ᵅ), α > 0 | regret: O(T^{max{1-3/7·α, 1/4}}) | Helped |
| Use OFTRL instead of the original experts approach when agent A₂ does not influence transitions | Agent A₁ in the two-agent MDP · Two-agent MDP with I₂ = 0 | regret: O(T^{1/2}) -> O(T^{1/4}) | Helped |
| Permit agent A₂ to change its policy by order Ω(1), rather than requiring its changes to decrease with T | Agent A₁'s learning problem · Two-agent MDP with ρ₂ = Ω(1) and I₂ = 1 | regret: O(poly(|S|) · T^β) for β < 1 | Hurt |
| Use periodic fixed-segment restarts rather than double recency bias | Agent A₁'s experts learner · Two-agent MDP with changing transitions | policy change smoothness | Hurt |
Closest papers by meaning
- Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms (NeurIPS 2024 · similarity 0.88)
- Online Markov Decision Processes Configuration with Continuous Decision Space (AAAI 2024 · similarity 0.88)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.88)
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.87)
- Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning (ICLR 2026 · similarity 0.87)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.