Research map / Reinforcement learning / Visual and representation RL
SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
Christopher Yeh, Victor Li, Rajeev Datta, Julio Arroyo, Nicolas Christianson, Chi Zhang, Yize Chen, Mohammad Mehdi Hosseini, Azarang Golmohammadi, Yuanyuan Shi, Yisong Yue, Adam Wierman
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 off-the-shelf RL algorithms (PPO, SAC, DDPG) instead of random actions | RL agents · EVChargingEnv | daily return | No clear effect |
| use multi-agent PPO with discrete actions instead of single-agent RL | PPO · EVChargingEnv | daily return | Improved |
| use multi-agent PPO instead of single-agent PPO | PPO · CogenEnv | daily return | Improved |
| use model predictive control instead of RL algorithms | RL baselines · DatacenterEnv and BuildingEnv | daily return | Improved |
| train on shifted environment (300MW wind) instead of original (0MW wind) | PPO and MA-PPO · CogenEnv, evaluated on shifted environment | daily return | Hurt |
| train on shifted MOER (2021) instead of original (2019) | RL agents · DatacenterEnv, evaluated on shifted environment | daily return | No clear effect |
| train on shifted environment (Summer 2021) instead of original (Summer 2019) | RL agents · EVChargingEnv, evaluated on shifted environment | daily return | Improved |
| train on shifted environment (Winter 2003) instead of original (Summer 2004) | RL agents · BuildingEnv, evaluated on shifted environment | daily return | Improved |
| use multi-agent policies trained on the original environment when tested under shift | RL agents · EVChargingEnv and CogenEnv | daily return | Improved |
Closest papers by meaning
- SustainDC: Benchmarking for Sustainable Data Center Control (NeurIPS 2024 · similarity 0.89)
- Carbon Footprint Reduction for Sustainable Data Centers in Real-Time (AAAI 2024 · similarity 0.88)
- Sustainability of Data Center Digital Twins with Reinforcement Learning (AAAI 2024 · similarity 0.86)
- LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers (NeurIPS 2025 · similarity 0.86)
- IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach (NeurIPS 2025 · similarity 0.85)
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.
