Expansive Latent Planning for Sparse Reward Offline Reinforcement Learning.
Robert GieselmannFlorian T. PokornyPublished in: CoRL (2023)
Keyphrases
- reinforcement learning
- action selection
- partially observable
- macro actions
- state space
- reward shaping
- reinforcement learning algorithms
- function approximation
- partially observable markov decision processes
- heuristic search
- model free
- complex domains
- reward function
- partially observable environments
- eligibility traces
- markov decision problems
- dynamic programming
- real time
- machine learning
- high dimensional
- optimal policy
- latent variables
- learning problems
- sparse data
- markov decision processes
- multi agent
- single agent
- optimal control
- stochastic domains
- reinforcement learning problems
- partial observability
- temporal difference
- action space
- state action
- long run
- infinite horizon
- inverse reinforcement learning
- learning process
- reinforcement learning methods
- average reward
- markov decision process
- decision theoretic
- probabilistic model
- compressive sensing
- ai planning