-
Notifications
You must be signed in to change notification settings - Fork 3
/
penalty.py
31 lines (27 loc) · 1.05 KB
/
penalty.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
# Copyright 2023 InstaDeep Ltd. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Game reference:
# -----------------
# Claus C, Boutilier C. The dynamics of reinforcement learning in
# cooperative multiagent systems. AAAI/IAAI. 1998.
# https://www.cs.toronto.edu/~cebly/Papers/_download_/multirl.pdf
import jax.numpy as jnp
penalty_games = {}
for penalty_value in (0, 25, 50, 75, 100):
penalty_games[f"{penalty_value}"] = jnp.array(
2
* [
[[-penalty_value, 0, 10], [0, 2, 0], [10, 0, -penalty_value]],
]
)