shariqiqbal2810 / MAAC

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

shariqiqbal2810/MAAC Issues

multi-agent particle environments
Closed 5 years ago8
issue thanks!
Updated 2 years ago
How to solve env_id?
Updated 2 years ago2
How to implement MADDPG+SAC and COMA+SAC
Updated 2 years ago1
About query, key and value input embedding
Closed 3 years ago1
How to visualize during training
Updated 3 years ago
The function names of "update_policies" and "update_critic" are reversed
Closed 3 years ago
Why does your implementation of MADDPG not work in your fork of MPE?
Updated 3 years ago
Critic encoders as shared modules ?
Closed 3 years ago3
Critic function learning
Updated 3 years ago
Where is the code to load the model？
Updated 3 years ago
Memory Leak
Closed 3 years ago1
Memory usage increases a lot when use the latest version of OpenAI baselines
Closed 3 years ago
Bias on value extractors ?
Updated 4 years ago
When I run "python main.py fullobs_collect_treasure V1" I meet error "ImportError: cannot import name 'Wall'"
Closed 4 years ago
How does the gradient back-propagate from Q to the action $a_i$？
Updated 4 years ago
How to visualize the attention weights between agents in the testing phase?
Closed 5 years ago8
question about reward
Closed 4 years ago10
About SAC implementation
Closed 4 years ago1
hello , i have a question on your paper
Updated 4 years ago1
Seeding fails to produce deterministic results
Closed 4 years ago9
Problem of optimizing policy
Closed 4 years ago4
does training advantage soft actor critic based on replay buffer has large bias?
Closed 4 years ago7
connection.py
Closed 4 years ago3
cannot handle some scenarios
Closed 4 years ago1
About the reporduction of experiment Cooperative Treasure Collection
Closed 4 years ago1
How to evaluate and test the training result?
Closed 5 years ago3
hi，my machine memory always overflow when I run your code,but I don't find the reason. Can you help me?
Closed 5 years ago1
when I run"python main.py fullobs_collect_treasure dir_1",there are the errors
Closed 5 years ago1
VecEnv, why closing the Pipe()
Closed 5 years ago2
How to run your code in other scenarios, i.e., cooperative navigation
Closed 5 years ago4
2 agents modification
Closed 5 years ago1
About environment
Closed 5 years ago1
State Action Encoding in Critic
Closed 5 years ago1
How to visualize the result?
Closed 5 years ago1
About the code
Closed 5 years ago1
About the results
Closed 5 years ago2