Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains.
Christian GumbschMartin V. ButzGeorg MartiusPublished in: CoRR (2021)
Keyphrases
- partially observable domains
- sensing actions
- partially observable
- planning problems
- belief state
- partial information
- reinforcement learning
- situation calculus
- partially observable markov decision processes
- latent variables
- heuristic search
- inverse reinforcement learning
- event calculus
- decision problems
- decision theoretic
- action selection
- ai planning
- initial state
- state space
- multi agent