Research map / Reinforcement learning / Policy gradient and actor-critic
Proximal Learning With Opponent-Learning Awareness
Stephen Zhao, Chris Lu, Roger Baker Grosse, Jakob Nicolaus Foerster
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 outer POLA instead of LOLA | One-step memory IPD with varied policy parameterizations · One-step memory IPD | runs finding TFT | Improved |
| Use outer POLA instead of LOLA | Pre-conditioned one-step memory IPD · One-step memory IPD | runs finding TFT | Improved |
| Replace tabular policies with neural-network policies | LOLA · One-step memory IPD | runs finding TFT | Hurt |
| Use POLA-DiCE instead of LOLA-DiCE | GRU policies · Full history IPD | reciprocity-based cooperation | Improved |
| Use opponent modeling | POLA-DiCE · Full history IPD | reciprocity-based cooperation | No clear effect |
| Use POLA-DiCE instead of LOLA-DiCE | GRU policies · Coin game | proportion of collected coins matching the agent's colour | Improved |
| Use opponent modeling | POLA-DiCE · Coin game | reciprocity-based cooperation | Hurt |
| Repeatedly train on the same samples for the outer loop (ablation) | POLA-DiCE · Social dilemma experiments | consistency of learning reciprocity-based cooperation | Hurt |
Closest papers by meaning
- Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents (NeurIPS 2024 · similarity 0.88)
- LOQA: Learning with Opponent Q-Learning Awareness (ICLR 2024 · similarity 0.87)
- Opponent Modeling based on Subgoal Inference (NeurIPS 2024 · similarity 0.86)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.86)
- An Open-Ended Learning Framework for Opponent Modeling (AAAI 2025 · similarity 0.86)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.86)
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.
