Skip to content
Road to Intelligence

Concept · Chapter 5: Vision, Speech & Reinforcement Learning

Actor–Critic Methods

Should knowUnderstand9 minDifficulty

Actor–critic methods train two parts together: an actor (the policy) that chooses actions and a critic (a value estimate) that judges them, giving the actor a lower-noise learning signal.

The problem

Pure policy gradients wait for whole-episode returns and are very noisy; pure value methods struggle with large or continuous action spaces.

The solution

Learn a value function alongside the policy and use it as the baseline, so the actor is updated by the advantage: how much better the action was than the critic expected.

The consequence

Faster, steadier learning; most modern deep RL algorithms, including PPO as usually implemented, are actor–critic.

A player and a coach

The actor plays. The critic watches each move and says "that went better than I expected" or "worse". The actor uses that judgement, rather than waiting for the final score, to decide what to reinforce. The critic improves its predictions from the same experience.

The signal

After a step from ss to s′s' with reward rr, the critic's TD error doubles as an estimate of the advantage:

A^=r+γV(s′)−V(s)\hat A = r + \gamma V(s') - V(s)

If A^>0\hat A > 0, the action beat expectations, so the actor raises its probability, exactly as in the policy-gradient update with G−bG - b replaced by A^\hat A. The critic, meanwhile, moves V(s)V(s) toward r+γV(s′)r + \gamma V(s'), the same temporal-difference idea as Q-learning.

Using the critic's one-step estimate instead of the full noisy return trades a little bias for a large reduction in variance. A3C (2016) ran many actors in parallel updating one shared actor–critic network Established, and PPO is typically implemented with a learned value function as its critic Established. In RLHF for language models, the critic predicts the reward-model score a partial response will end up with.

What to remember

  • Actor: π(a | s), decides. Critic: V(s), predicts the return.
  • Advantage ≈ r + γV(s′) − V(s): better or worse than the critic expected.
  • The critic is trained like Q-learning's TD update; the actor like a policy gradient.

Key papers

Optional

Asynchronous Methods for Deep Reinforcement Learning

Volodymyr Mnih, Adrià Puigdomènech Badia et al. · 2016 · ICML 2016

A3C: a widely used deep actor–critic method, with many parallel actors sharing one network.

~35 min readarXiv:1602.01783✓ verified 2026-09-26
Essential

Proximal Policy Optimization Algorithms

John Schulman, Filip Wolski et al. · 2017

PPO: a simple, robust actor–critic policy-gradient method. It became the default RL algorithm in many labs and was the optimiser in InstructGPT-style RLHF.

~30 min readarXiv:1707.06347✓ verified 2026-09-26