Sequential Planning in Large Partially Observable Environments guided by LLMs.
Swarna Kamal PaulPublished in: CoRR (2023)
Keyphrases
- partially observable environments
- partially observable
- partially observable markov decision processes
- inverse reinforcement learning
- planning problems
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- dynamical systems
- decision problems
- special case
- mobile robot
- state space
- heuristic search
- infinite horizon
- cooperative games