Reinforcement Learning for Control
by Community · free · Last verified 2026-03-17
Trains control policies for autonomous systems through environment interaction and reward signals using model-free (PPO, SAC, TD3) and model-based (MBPO, Dreamer) RL algorithms. Enables superhuman performance in complex continuous control tasks from locomotion to manipulation.
https://stable-baselines3.readthedocs.io/ ↗B
B—Above Average
Adoption: B+Quality: AFreshness: A+Citations: AEngagement: F
Specifications
- License
- MIT
- Pricing
- free
- Capabilities
- PPO-SAC-TD3, model-based-RL, multi-agent-RL, reward-shaping, sim-based-policy-training
- Integrations
- Stable Baselines3, RLlib, Gymnasium, Isaac Lab, Brax
- Use Cases
- Legged robot locomotion policy learning, HVAC energy optimization control, Robotic manipulation skill acquisition
- API Available
- No
- Difficulty
- advanced
- Prerequisites
- machine-learning, control-theory, simulation
- Supported Agents
- Tags
- reinforcement-learning, control, autonomous-systems, policy-optimization
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
69.9Adoption
78
Quality
87
Freshness
90
Citations
85
Engagement
0