Adapting Image-based RL Policies via Predicted Rewards.
Weiyao WangXinyuan FangGregory D. HagerPublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- optimal policy
- markov decision processes
- reward function
- control policy
- total reward
- control policies
- markov decision process
- discounted reward
- reinforcement learning algorithms
- policy search
- state space
- long run
- semi markov decision process
- partially observable markov decision processes
- hierarchical reinforcement learning
- markov decision problems
- function approximation
- decision problems
- average reward
- expected reward
- model free
- computer vision
- finite state
- finite horizon
- dynamic programming
- partially observable
- average cost
- action space
- sufficient conditions
- policy iteration
- action selection
- reinforcement learning agents
- long term and short term
- multiagent reinforcement learning
- reinforcement learning methods
- learning problems
- learning algorithm
- multiple agents
- transition probabilities
- partially observable domains
- machine learning
- neural network