Use this reinforcement-learning update to study policy evaluation or gradient-based learning in a fully specified environment with explicit states, actions, rewards, discounting, and sampling behavior.

Rewards

Required list input.

State values

Required list input.

Action log probabilities

Required list input.

Policy entropies

Required list input.

Bootstrap value

Required number input.

Discount factor

Required number input.

Value loss coefficient

Required number input.

Entropy coefficient

Required number input.

Calculate discounted returns, advantages, and A3C rollout losses. The tool evaluates the supplied inputs together and returns the named outputs below; it does not infer omitted operating conditions or change the units shown.^[1]

A3C rollout update

The resulting a3c rollout update returned as an object.

• Estimates can be biased or high-variance and depend on exploration, bootstrapping, function approximation, rollout length, advantage normalization, off-policy corrections, seeds, and environment stationarity. Training return does not establish safe deployment.
• Use finite inputs in the displayed units and preserve more precision than the final presentation requires. Independently verify safety-critical, financial, compliance, or production decisions.

Test tabular cases, run multiple seeds, report confidence intervals and sample cost, evaluate off-policy and under perturbations, and apply domain safety constraints.

• Policy-Gradient Training Step

  Apply one categorical REINFORCE policy-gradient update from an action, return, and baseline.

• Reinforcement-Learning Policy Evaluator

  Evaluate a fixed finite-state policy by iterating rewards and its transition matrix.

• Chain Ladder Development Factor Calculator

  Calculate the volume-weighted chain ladder age-to-age development factor from paired cumulative losses.