search

FLAIROx / JaxMARL

Multi-Agent Reinforcement Learning with JAX
Apache License 2.0
393 stars 68 forks source link

made coin game compatible with iql_rnn #107

Open Dronie opened 1 month ago

Dronie commented 1 month ago

Slightly changed the way observations, rewards, dones and infos are processed/returned to make coin game compatible with iql_rnn (and potentially others but this is the only algorithm I tested). Also added line 352 which allows for shared rewards (each agent's reward becomes the sum of their individual rewards) but not yet integrated in a nice way.

See plots for training results (using same configs as in ql_rnn_mpe): image

Also see gifs of trained policies in action (10 episodes each): Default (individual) rewards: individual_rewards

Shared rewards: shared_rewards

NB: have not done unit tests as this is only a minor change to an existing environment - let me know if this is an issue!

amacrutherford commented 1 month ago

hey thanks for opening this :) we're busy with neurips rebuttals atm but will come back to this after!

amacrutherford commented 4 days ago

Hey! just took a look and it looks good but could you add a flag for shared vs individual rewards? @Dronie

Dronie commented 4 days ago

Hey! just took a look and it looks good but could you add a flag for shared vs individual rewards? @Dronie

Done :)