policy (in rl)

1 episode mention this concept

Related concepts — line thickness indicates connection strength. Click any node to explore.

Related concepts

Concepts that appear alongside policy (in rl) across episodes.

• reinforcement learning agent
• trial and error
• reward structure / reward function
• simulation-to-real gap / transfer learning
• ai safety
• unsupervised learning
• value function
• deep reinforcement learning (deep rl)
• deep q-networks (dqn)
• stochastic vs. deterministic environments
• deep neural networks
• model-based rl
• model-free rl
• environment model
• loss function
• q-learning
• sequential decisions
• discounted reward
• supervised learning