value-based reinforcement learning method
C9067
concept
A value-based reinforcement learning method is an approach that learns a value function estimating expected future rewards for states or state-action pairs and derives a policy by selecting actions that maximize these estimated values.
Observed surface forms (2)
- Deep Q-Network variant ×2
- reinforcement learning technique ×1
Instances (4)
- Atari deep Q-network
- Dueling DQN
- Prioritized Experience Replay DQN via concept surface "Deep Q-Network variant"
- Hindsight Experience Replay via concept surface "reinforcement learning technique"