proroklab / rllib_differentiable_comms
This is a minimal example to demonstrate how multi-agent reinforcement learning with differentiable communication channels and centralized critics can be realized in RLLib. This example serves as a reference implementation and starting point for making RLLib more compatible with such architectures.
☆42Updated last year
Alternatives and similar repositories for rllib_differentiable_comms
Users that are interested in rllib_differentiable_comms are comparing it to the libraries listed below
Sorting:
- Partially Observable Process Gym☆189Updated 10 months ago
- Benchmarking RL generalization in an interpretable way.☆156Updated 2 months ago
- A tool for aggregating and plotting MARL experiment data.☆77Updated 3 months ago
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆76Updated 8 months ago
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL☆42Updated 8 months ago
- ☆229Updated 5 months ago
- Author's PyTorch implementation of TD7 for online and offline RL☆143Updated last year
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 3 years ago
- Datasets with baselines for offline multi-agent reinforcement learning.☆167Updated this week
- Code for MOPO: Model-based Offline Policy Optimization☆178Updated 2 years ago
- Implementation of Trajectory Transformer with attention caching and batched beam search☆111Updated 2 years ago
- The Starcraft Multi-Agent challenge lite☆42Updated 8 months ago
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆43Updated last month
- Gridworld for MARL experiments☆140Updated 4 years ago
- Baseline implementation of recurrent PPO using truncated BPTT☆142Updated last year
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆46Updated 8 months ago
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆167Updated 3 years ago
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆91Updated 8 months ago
- ☆111Updated 2 years ago
- ☆31Updated 4 years ago
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆89Updated 2 months ago
- Evaluating long-term memory of reinforcement learning algorithms☆142Updated last year
- Conservative Q Learning on top of SAC☆130Updated 2 years ago
- ☆195Updated 2 years ago
- PyTorch implementation of the Option-Critic framework, Harb et al. 2016☆128Updated 9 months ago
- Clean baseline implementation of PPO using an episodic TransformerXL memory☆178Updated 10 months ago
- A collection of recent MARL papers☆91Updated 5 months ago
- Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/☆96Updated 4 years ago
- 🤖 Elegant implementations of offline safe RL algorithms in PyTorch☆202Updated 8 months ago
- Diversity is All You Need: Learning Skills without a Reward Function in PyTorch.☆68Updated last year