Skip to main content

Action Space

In short

The set of decisions the RL agent can make — buy, sell, hold fractions

The action space defines what choices the AI can make. A simple agent has 3 actions: buy, sell, hold. A more sophisticated one can trade any fraction of its portfolio. More actions = more flexibility but harder to train.

The action space for trading RL agents can be discrete (buy/sell/hold) or continuous (fractional position sizes). Continuous action spaces allow precise position sizing but require more training. Bounded actions prevent leverage or short-selling in constrained configurations.

Related concepts

  • Reinforcement Learning — RL is how an AI learns to make decisions by trying things and getting rewards or penalties. Think of training a dog — good moves get treats, bad moves get nothing. The AI keeps adjusting until it finds the best strategy.
  • Observation Space — The observation space is everything the AI trading agent can see before making a decision. It might include price data, technical indicators, sentiment scores, and portfolio state. More useful data = better decisions (up to a point).
  • PPO Algorithm — PPO is one of the best algorithms for training AI agents. It learns slowly and steadily instead of making wild policy changes that could destabilize training. Think of it as a careful student who improves step by step.