qrdqn#

Source code: tianshou/algorithm/modelfree/qrdqn.py

class QRDQNPolicy(*, model: TModel, action_space: Space, observation_space: Space | None = None, eps_training: float = 0.0, eps_inference: float = 0.0)[source]#

Bases: DiscreteQLearningPolicy

Parameters:

  • model – a model mapping (obs, state, info) to action_values_BA.

  • action_space – the environment’s action space

  • observation_space – the environment’s observation space.

  • eps_training – the epsilon value for epsilon-greedy exploration during training. When collecting data for training, this is the probability of choosing a random action instead of the action chosen by the policy. A value of 0.0 means no exploration (fully greedy) and a value of 1.0 means full exploration (fully random).

  • eps_inference – the epsilon value for epsilon-greedy exploration during inference, i.e. non-training cases (such as evaluation during test steps). The epsilon value is the probability of choosing a random action instead of the action chosen by the policy. A value of 0.0 means no exploration (fully greedy) and a value of 1.0 means full exploration (fully random).

compute_q_value(logits: Tensor, mask: ndarray | None) → Tensor[source]#

Compute the q value based on the network’s raw output and action mask.

class QRDQN(*, policy: TQRDQNPolicy, optim: OptimizerFactory, gamma: float = 0.99, num_quantiles: int = 200, n_step_return_horizon: int = 1, target_update_freq: int = 0)[source]#

Bases: QLearningOffPolicyAlgorithm[TQRDQNPolicy], Generic[TQRDQNPolicy]

Implementation of Quantile Regression Deep Q-Network. arXiv:1710.10044.

Parameters:

  • policy – the policy

  • optim – the optimizer factory for the policy’s model.

  • gamma – the discount factor in [0, 1] for future rewards. This determines how much future rewards are valued compared to immediate ones. Lower values (closer to 0) make the agent focus on immediate rewards, creating “myopic” behavior. Higher values (closer to 1) make the agent value long-term rewards more, potentially improving performance in tasks where delayed rewards are important but increasing training variance by incorporating more environmental stochasticity. Typically set between 0.9 and 0.99 for most reinforcement learning tasks

  • num_quantiles – the number of quantiles used to represent the return distribution for each action. Determines the granularity of the approximated distribution function. Higher values provide a more fine-grained approximation of the true return distribution but increase computational and memory requirements. Lower values reduce computational cost but may not capture the distribution accurately enough. The original QRDQN paper used 200 quantiles for Atari environments. Must be greater than 1, as at least two quantiles are needed to represent a distribution.

  • n_step_return_horizon – the number of future steps (> 0) to consider when computing temporal difference (TD) targets. Controls the balance between TD learning and Monte Carlo methods: higher values reduce bias (by relying less on potentially inaccurate value estimates) but increase variance (by incorporating more environmental stochasticity and reducing the averaging effect). A value of 1 corresponds to standard TD learning with immediate bootstrapping, while very large values approach Monte Carlo-like estimation that uses complete episode returns.

  • target_update_freq – the number of training iterations between each complete update of the target network. Controls how frequently the target Q-network parameters are updated with the current Q-network values. A value of 0 disables the target network entirely, using only a single network for both action selection and bootstrap targets. Higher values provide more stable learning targets but slow down the propagation of new value estimates. Lower positive values allow faster learning but may lead to instability due to rapidly changing targets. Typically set between 100-10000 for DQN variants, with exact values depending on environment complexity.