Agents

Create and configure reinforcement learning agents using common algorithms, such as SARSA, DQN, DDPG, and A2C

A reinforcement learning agent receives observations and a reward from the environment. Using its policy, the agent selects an action based on the observations and reward, and sends the action to the environment. During training, the agent continuously updates the policy parameters based on the action, observations, and reward. Doing so, allows the agent to learn the optimal policy for the given environment and reward signal.

Reinforcement Learning Toolbox™ software provides reinforcement learning agents that use several common algorithms, such as SARSA, DQN, DDPG, and A2C. You can also implement other agent algorithms by creating your own custom agents.

For more information, see Reinforcement Learning Agents. For more information on defining policy representations, see Create Policy and Value Function Representations.

Functions

expand all

rlQAgentQ-learning reinforcement learning agent
rlSARSAAgentSARSA reinforcement learning agent
rlDQNAgentDeep Q-network reinforcement learning agent
rlPGAgentPolicy gradient reinforcement learning agent
rlDDPGAgentDeep deterministic policy gradient reinforcement learning agent
rlTD3AgentTwin-delayed deep deterministic policy gradient reinforcement learning agent
rlACAgentActor-critic reinforcement learning agent
rlPPOAgentProximal policy optimization reinforcement learning agent
rlSACAgentSoft actor-critic reinforcement learning agent
rlQAgentOptionsOptions for Q-learning agent
rlSARSAAgentOptionsOptions for SARSA agent
rlDQNAgentOptionsOptions for DQN agent
rlPGAgentOptionsOptions for PG agent
rlDDPGAgentOptionsOptions for DDPG agent
rlTD3AgentOptionsOptions for TD3 agent
rlACAgentOptionsOptions for AC agent
rlPPOAgentOptionsOptions for PPO agent
rlSACAgentOptionsOptions for SAC agent
rlAgentInitializationOptionsOptions for initializing reinforcement learning agents
getActorGet actor representation from reinforcement learning agent
getCriticGet critic representation from reinforcement learning agent
setActorSet actor representation of reinforcement learning agent
setCriticSet critic representation of reinforcement learning agent
getActionObtain action from agent or actor representation given environment observations

Topics

Reinforcement Learning Agents

You can create an agent using one of several standard reinforcement learning algorithms or define your own custom agent.

Q-Learning Agents

Create Q-learning agents for reinforcement learning.

SARSA Agents

Create SARSA agents for reinforcement learning.

Deep Q-Network Agents

Create DQN agents for reinforcement learning.

Policy Gradient Agents

Create PG agents for reinforcement learning.

Deep Deterministic Policy Gradient Agents

Create DDPG agents for reinforcement learning.

Twin-Delayed Deep Deterministic Policy Gradient Agents

Create DDPG agents for reinforcement learning.

Actor-Critic Agents

Create AC agents for reinforcement learning.

Proximal Policy Optimization Agents

Create PPO agents for reinforcement learning.

Soft Actor-Critic Agents

Create SAC agents for reinforcement learning.

Custom Agents

Create agents that use custom reinforcement learning algorithms.