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.
☆41Updated 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.☆147Updated this week
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆72Updated 6 months ago
- Partially Observable Process Gym☆181Updated 8 months ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 2 years ago
- A tool for aggregating and plotting MARL experiment data.☆73Updated last month
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL☆41Updated 6 months ago
- ☆31Updated 3 years ago
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆42Updated 5 months ago
- Conservative Q Learning on top of SAC☆126Updated 2 years ago
- The Starcraft Multi-Agent challenge lite☆42Updated 6 months ago
- Code for MOPO: Model-based Offline Policy Optimization☆174Updated 2 years ago
- PyTorch implementation of the Option-Critic framework, Harb et al. 2016☆122Updated 7 months ago
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆165Updated 2 years ago
- ☆41Updated last year
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.☆69Updated last year
- Simple maze environments using mujoco-py☆54Updated last year
- Baseline implementation of recurrent PPO using truncated BPTT☆137Updated 10 months ago
- Author's PyTorch implementation of TD7 for online and offline RL☆136Updated last year
- Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination☆26Updated 2 years ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆93Updated 4 months ago
- Implementation of Trajectory Transformer with attention caching and batched beam search☆109Updated last year
- Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/☆93Updated 4 years ago
- ☆193Updated last year
- Prioritized Experience Replay implementation with proportional prioritization☆76Updated last year
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆34Updated 2 years ago
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆147Updated 3 years ago
- 🤖 Elegant implementations of offline safe RL algorithms in PyTorch☆194Updated 6 months ago
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆88Updated 6 months ago
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆19Updated last year
- ☆74Updated 9 months ago