Merge branch 'main' into extend-bpd-ig

Farama-Foundation · Jun 18, 2024 · ceb2473 · ceb2473
2 parents 3dd6dfb + 2be31ad
commit ceb2473
Show file tree

Hide file tree

Showing 36 changed files with 3,684 additions and 3,141 deletions.
diff --git a/README.md b/README.md
@@ -66,7 +66,7 @@ env = LinearizeReward(env, weights)
 
 For details on multi-objective multi-agent RL definitions, see [Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey](https://arxiv.org/abs/1909.02964).
 
-You can also check more examples in this colab notebook! [![MOMAland Demo in Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Farama-Foundation/momaland/blob/doc/notebook/momaland_demo.ipynb)
+You can also check more examples in this colab notebook! [![MOMAland Demo in Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Farama-Foundation/momaland/blob/main/momaland_demo.ipynb)
 <!-- end snippet-usage -->
 
 ## Learning Algorithms

diff --git a/docs/environments/all-envs.md b/docs/environments/all-envs.md
@@ -20,7 +20,7 @@ More information are available in the TODO [MOMAland paper]().
 | [`mo-beach-v0`](https://momaland.farama.org/environments/mobeach/) <br><img src="https://momaland.farama.org/_static/gifs/mobeach.gif" width="400px">                                      | Any                     | Discrete / Discrete     | `[occupation, mixture]`                                          | Taken from [Mannion_2018](https://www.cambridge.org/core/journals/knowledge-engineering-review/article/reward-shaping-for-knowledgebased-multiobjective-multiagent-reinforcement-learning/75F1507F7CAC7C6625F87AE7CD344D52). MO-Beach is a game with two objectives, reflecting the enjoyment of tourists (agents) on their respective beach sections in terms of crowdedness and diversity of attendees. Each beach section is characterised by a capacity and each agent is characterised by a type.                                                                                                                                                                                                                                                                                                                                              |
 | [`mo-item-gathering-v0`](https://momaland.farama.org/environments/moitem_gathering/) <br><img src="https://momaland.farama.org/_static/gifs/moitem_gathering.gif" width="400px">           | Adversarial             | Discrete / Discrete     | `[#objects]` (configurable)                                      | Adapted from [Kallstrom_2019](https://www.diva-portal.org/smash/get/diva2:1362933/FULLTEXT01.pdf), is a multi-agent grid world, containing items of different colours. Each colour represents a different objective and the goal of the agents is to collect as many objects as possible.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | [`mo-gem-mining-v0`](https://momaland.farama.org/environments/mogem_mining/) <br><img src="https://momaland.farama.org/_static/gifs/mogem_mining.gif" width="400px">                       | Cooperative             | - / Discrete            | `[#gems]` (configurable)                                         | MO version of Gem Mining [Bargiacchi_2018](https://proceedings.mlr.press/v80/bargiacchi18a/bargiacchi18a.pdf). Agents go to different mines to extract different gems (objectives). There are restrictions on which mines can be reached for each agent. Agents also influence each other's producitivity.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-| [`mo-congestion-v0`](https://momaland.farama.org/environments/mocongestion/) <br><img src="https://momaland.farama.org/_static/gifs/mocongestion.gif" width="400px">                       | Adversarial             | - / Discrete            | `[travel time, cost]`                                            | MO-RouteChoice is a multi-objective extension of the route choice problem [Thomasini_2023](https://alaworkshop2023.github.io/papers/ALA2023_paper_69.pdf), where a number of self-interested drivers (agents) must navigate a road network.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| [`mo-route_choice-v0`](https://momaland.farama.org/environments/mo_routechoice/) <br><img src="https://momaland.farama.org/_static/gifs/mo_routechoice.gif" width="400px">                 | Adversarial             | - / Discrete            | `[travel time, cost]`                                            | MO-RouteChoice is a multi-objective extension of the route choice problem [Thomasini_2023](https://alaworkshop2023.github.io/papers/ALA2023_paper_69.pdf), where a number of self-interested drivers (agents) must navigate a road network.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 | [`mo-pistonball-v0`](https://momaland.farama.org/environments/mopistonball/) <br><img src="https://momaland.farama.org/_static/gifs/mopistonball.gif" width="400px">                       | Cooperative             | Continuous / Any        | `[agent_#n_reward]` (configurable)                               | An MO version of [PZ's Pistonball](https://pettingzoo.farama.org/environments/butterfly/pistonball/) where the reward of each agent is kept separate.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | [`mo-multiwalker-stability-v0`](https://momaland.farama.org/environments/momultiwalker_stabilty/) <br><img src="https://momaland.farama.org/_static/gifs/momultiwalker.gif" width="400px"> | Cooperative             | Continuous / Continuous | `[progress right, package stability]`                            | A MO version of [PZ's MultiWalker](https://pettingzoo.farama.org/environments/sisl/multiwalker/) introduced in [Gupta_2017](https://link.springer.com/chapter/10.1007/978-3-319-71682-4_5), where the agents also seek to keep the package steady.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | [`catch-v0`](https://momaland.farama.org/environments/catch/) <br><img src="https://momaland.farama.org/_static/gifs/catch.gif" width="400px">                                             | Cooperative             | Continuous / Continuous | `[distance_target, distance_other_drones]`                       | Agents must corner and catch a target drone while maintaining distance between themselves.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |

diff --git a/docs/environments/mocongestion.md b/docs/environments/mocongestion.md
diff --git a/docs/environments/moroute_choice.md b/docs/environments/moroute_choice.md
@@ -0,0 +1,23 @@
+---
+autogenerated:
+title: MO-RouteChoice
+firstpage:
+---
+
+# MO-RouteChoice
+
+|   |                                   |
+|---|-----------------------------------|
+| Agents names | `agent_i for i in [0, 4199]`      |
+| Action Space | Discrete(3)                       |
+| Observation Space | Box(0.0, 4200.0, (1,), float32)   |
+| Reward Space | Box(-3.0, 0.0, (2,), float32)     |
+| Import | `momaland.envs.mo_routechoice_v0` |
+
+Environment for MO-RouteChoice problem.
+
+The init method takes in environment arguments and should define the following attributes:
+- possible_agents
+- action_spaces
+- observation_spaces
+These attributes should not be changed after initialization.
diff --git a/momaland/envs/congestion/mocongestion_v0.py b/momaland/envs/congestion/mocongestion_v0.py
diff --git a/momaland/envs/congestion/__init__.py → momaland/envs/route_choice/__init__.py b/momaland/envs/congestion/__init__.py → momaland/envs/route_choice/__init__.py
@@ -1,4 +1,4 @@
-"""MO Congestion Game.
+"""MO Route Choice Game.
 
 From De Oliveira Ramos, G., Radulescu, R., Nowe, A., Tavares, A. (2020).
 Toll-Based Learning for Minimising Congestion under Heterogeneous Preferences.

diff --git a/momaland/envs/route_choice/moroute_choice_v0.py b/momaland/envs/route_choice/moroute_choice_v0.py
@@ -0,0 +1,5 @@
+"""Route choice environment for multi-objective optimization."""
+from momaland.envs.route_choice.route_choice import env, parallel_env, raw_env
+
+
+__all__ = ["env", "parallel_env", "raw_env"]
diff --git a/...and/envs/congestion/networks/Anaheim.json → ...d/envs/route_choice/networks/Anaheim.json b/...and/envs/congestion/networks/Anaheim.json → ...d/envs/route_choice/networks/Anaheim.json
diff --git a/...n/networks/BBraess_1_2100_10_c1_2100.json → ...e/networks/BBraess_1_2100_10_c1_2100.json b/...n/networks/BBraess_1_2100_10_c1_2100.json → ...e/networks/BBraess_1_2100_10_c1_2100.json
diff --git a/...on/networks/BBraess_3_2100_10_c1_900.json → ...ce/networks/BBraess_3_2100_10_c1_900.json b/...on/networks/BBraess_3_2100_10_c1_900.json → ...ce/networks/BBraess_3_2100_10_c1_900.json
diff --git a/...on/networks/BBraess_5_2100_10_c1_900.json → ...ce/networks/BBraess_5_2100_10_c1_900.json b/...on/networks/BBraess_5_2100_10_c1_900.json → ...ce/networks/BBraess_5_2100_10_c1_900.json
diff --git a/...on/networks/BBraess_7_2100_10_c1_900.json → ...ce/networks/BBraess_7_2100_10_c1_900.json b/...on/networks/BBraess_7_2100_10_c1_900.json → ...ce/networks/BBraess_7_2100_10_c1_900.json