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
Related projects ⓘ
Alternatives and complementary repositories for rllib_differentiable_comms
- Benchmarking RL generalization in an interpretable way.☆133Updated 9 months ago
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆40Updated 2 months ago
- Partially Observable Process Gym☆167Updated 4 months ago
- Author's PyTorch implementation of TD7 for online and offline RL☆117Updated last year
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆63Updated 2 months ago
- A tool for aggregating and plotting MARL experiment data.☆63Updated 3 weeks ago
- Conservative Q Learning on top of SAC☆121Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆99Updated 2 years ago
- PyTorch implementation of the Option-Critic framework, Harb et al. 2016☆117Updated 3 months ago
- The Starcraft Multi-Agent challenge lite☆38Updated 2 months ago
- Baseline implementation of recurrent PPO using truncated BPTT☆125Updated 6 months ago
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL☆35Updated 2 months ago
- Datasets with baselines for offline multi-agent reinforcement learning.☆145Updated 2 weeks ago
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆32Updated 3 weeks ago
- Simple maze environments using mujoco-py☆52Updated 10 months ago
- Representation Learning for RL☆119Updated last year
- Source code for "A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning" (ICML 2021)☆32Updated 2 years ago
- Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/☆90Updated 3 years ago
- ☆190Updated last year
- Diversity is All You Need: Learning Skills without a Reward Function in PyTorch.☆60Updated last year
- Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.☆114Updated 3 years ago
- Prioritized Experience Replay implementation with proportional prioritization☆70Updated last year
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆157Updated 2 years ago
- ☆54Updated 8 months ago
- ☆38Updated last year
- Author's Pytorch implementation of ICLR2023 paper Behavior Proximal Policy Optimization (BPPO).☆73Updated 11 months ago
- PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tu…☆131Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆62Updated last year
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆77Updated 2 months ago
- PyTorch Implementation of FeUdal Networks for Hierarchical Reinforcement Learning (FuNs), Vezhnevets et al. 2017.☆38Updated 4 years ago