Adapting Image-based RL Policies via Predicted Rewards.
Weiyao WangXinyuan FangGregory D. HagerPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- markov decision processes
- reward function
- control policy
- total reward
- control policies
- markov decision process
- reinforcement learning algorithms
- discounted reward
- semi markov decision process
- policy search
- state space
- partially observable markov decision processes
- markov decision problems
- hierarchical reinforcement learning
- average reward
- decision problems
- reinforcement learning agents
- long run
- finite horizon
- model free
- partially observable
- expected reward
- machine learning
- function approximation
- finite state
- dynamic programming
- computer vision
- multiple agents
- sufficient conditions
- action space
- policy iteration
- average cost
- action selection
- state and action spaces
- partially observable domains
- multi agent
- learning algorithm
- bandit problems
- multiagent reinforcement learning
- actor critic
- stationary policies
- learning agents
- learning classifier systems