Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add ProcGoalEnv. #30

Merged
merged 6 commits into from
Jun 30, 2020
Merged
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions src/seals/diagnostics/proc_goal.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
"""Gridworld with large random initial state."""
"""Large gridworld with random agent and goal position."""

from gym import spaces
import numpy as np
Expand All @@ -7,7 +7,7 @@


class ProcGoalEnv(base_envs.ResettableMDP):
"""Gridworld with large random initial state.
"""Large gridworld with random agent and goal position.

In this task, the agent starts at a random position in a large
grid, and must navigate to a goal randomly placed in a
Expand All @@ -23,9 +23,9 @@ def __init__(self, bounds: int = 100, distance: int = 10):
"""Constructs environment.

Args:
bounds: the absolute values of the agent's coordinates are
bounded by `bounds`. Increasing the value might make
generalization harder.
bounds: the absolute values of the coordinates of the initial agent
position are bounded by `bounds`. Increasing the value might make
pedrofreire marked this conversation as resolved.
Show resolved Hide resolved
generalization harder.
pedrofreire marked this conversation as resolved.
Show resolved Hide resolved
distance: initial distance between agent and goal.
"""
self._bounds = bounds
Expand Down