Cs5446 Ai Planning And Decision Making -

| Feature | CS5446 (Planning) | Reinforcement Learning | | :--- | :--- | :--- | | | Known (given transition probabilities/rewards) | Unknown (must be explored) | | Primary Focus | Computation: computing the optimal policy from a known model | Learning: estimating the value function from experience | | Algorithm Type | Dynamic Programming, Heuristic Search | Temporal Difference (Q-learning, SARSA), Policy Gradients | | Sample Efficiency | High (no interaction needed) | Low (needs thousands of episodes) | | Use Case | Robotics simulation, logistics, automated verification | Game playing (Atari, Go), real-world interaction where a model is hard to specify |

Whether you are a graduate student preparing for research in autonomous systems, an engineer building the next generation of warehouse robots, or a researcher combining planning with deep learning, the concepts of MDPs, heuristics, and formal state-space search are indispensable. cs5446 ai planning and decision making

uses LLMs to translate human instructions into PDDL, then uses a classical planner (from CS5446) to generate verified action sequences. Conversely, LLMs can act as heuristics to guide planners in massive state spaces. | Feature | CS5446 (Planning) | Reinforcement Learning

A central component of the curriculum is PDDL. Students learn to model the world not just as data, but as logical states. In PDDL, one defines: A central component of the curriculum is PDDL

CS5446 introduces concepts from Game Theory

The math isn't the hardest part. The logic isn't either.