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.
☆40Updated 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.☆142Updated last week
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆101Updated 2 years ago
- Author's PyTorch implementation of TD7 for online and offline RL☆127Updated last year
- PyTorch implementation of the Option-Critic framework, Harb et al. 2016☆122Updated 6 months ago
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL☆36Updated 5 months ago
- A tool for aggregating and plotting MARL experiment data.☆71Updated last month
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆42Updated 5 months ago
- Gridworld for MARL experiments☆138Updated 4 years ago
- Baseline implementation of recurrent PPO using truncated BPTT☆134Updated 9 months ago
- Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.☆118Updated 3 years ago
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆39Updated last month
- Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination☆26Updated 2 years ago
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆72Updated 5 months ago
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆87Updated 5 months ago
- Representation Learning for RL☆121Updated last year
- Source code for "A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning" (ICML 2021)☆31Updated 2 years ago
- The Starcraft Multi-Agent challenge lite☆41Updated 5 months ago
- ☆30Updated 3 years ago
- Code for MOPO: Model-based Offline Policy Optimization☆173Updated 2 years ago
- A collection of recent MARL papers☆85Updated 3 months ago
- Simple maze environments using mujoco-py☆54Updated last year
- ☆191Updated last year
- Datasets with baselines for offline multi-agent reinforcement learning.☆160Updated 2 weeks ago
- Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)☆52Updated 2 years ago
- This is a repository for Hidden-utility Self-Play.☆26Updated last year
- Implementation of Trajectory Transformer with attention caching and batched beam search☆109Updated last year
- Partially Observable Process Gym☆178Updated 7 months ago
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆146Updated 3 years ago
- Implemention of the Decision-Pretrained Transformer (DPT) from the paper Supervised Pretraining Can Learn In-Context Reinforcement Learni…☆57Updated 8 months ago
- Official repository for paper "Conservative Offline Distributional Reinforcement Learning" (NeurIPS 2021)☆21Updated 3 years ago