gxm.wrappers#
|
Base class for wrappers in gxm, over either bare Dynamics or an Environment. |
|
Base class for wrappers that only operate on Environments (need reward/terminated/truncated). |
|
Wrapper that automatically resets an environment on episode end. |
|
Wrapper that clips the reward to a specified range. |
|
Wrapper that discretizes a continuous action space. |
|
A wrapper that counts the number of episodes completed in the environment. |
|
A wrapper that makes losing a life in an environment (like Atari games) count as the end of an episode. |
|
|
|
Wrapper that adds a rollout method to the environment. |
|
A wrapper that treats truncation as termination. |
|
A wrapper that records the episode length \(T\) , episodic return \(J(\tau) = \sum_{t=0}^{T} r_t\) , and discounted episodic return \(G(\tau) = \sum_{t=0}^{T} \gamma^t r_t\) at the end of each episode. |
|
Wrapper that stacks the observation along a new axis. |
|
A wrapper that counts the number of steps taken in the environment. |
|
A wrapper that makes actions sticky with a given probability. |
|
Wrapper that terminates an episode after a fixed number of steps. |