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
- Benchmarking RL generalization in an interpretable way.☆153Updated last month
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆73Updated 7 months ago
- PyTorch implementation of the Option-Critic framework, Harb et al. 2016☆126Updated 8 months ago
- Partially Observable Process Gym☆186Updated 9 months ago
- ☆31Updated 3 years ago
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆44Updated 7 months ago
- A tool for aggregating and plotting MARL experiment data.☆77Updated 3 months ago
- The Starcraft Multi-Agent challenge lite☆42Updated 7 months ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 2 years ago
- Implementation of Trajectory Transformer with attention caching and batched beam search☆111Updated last year
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL☆41Updated 7 months ago
- Author's PyTorch implementation of TD7 for online and offline RL☆141Updated last year
- Datasets with baselines for offline multi-agent reinforcement learning.☆164Updated 2 weeks ago
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆43Updated 3 weeks ago
- Repo for the multi-agent PressurePlate environment☆16Updated 3 years ago
- Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.☆36Updated 2 months ago
- Baseline implementation of recurrent PPO using truncated BPTT☆140Updated 11 months ago
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.☆71Updated last year
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆167Updated 3 years ago
- Model-Based Offline Reinforcement Learning☆50Updated 4 years ago
- Simple maze environments using mujoco-py☆54Updated last year
- ☆224Updated 5 months ago
- ☆109Updated 2 years ago
- Level-based Foraging (LBF): A multi-agent environment for RL☆178Updated 7 months ago
- Code for MOPO: Model-based Offline Policy Optimization☆177Updated 2 years ago
- Deep Hierarchical Planning from Pixels☆96Updated 2 years ago
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆87Updated last month
- ☆44Updated last year
- ☆31Updated 2 years ago
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆19Updated last year