d-corsi / SafeRL
A set of algorithms and environments to train SafeRL agents, written in TensorFlow2 and OpenAI Gym.
☆10Updated 2 years ago
Alternatives and similar repositories for SafeRL:
Users that are interested in SafeRL are comparing it to the libraries listed below
- qmix☆22Updated 4 years ago
- PyTorch implementation of MATD3☆13Updated 4 years ago
- ☆39Updated 3 years ago
- ☆83Updated 3 years ago
- A novel preference-driven multi-objective reinforcement learning algorithm using a single policy network that covers the entire preferenc…☆26Updated last year
- ☆20Updated 5 years ago
- Constrained Policy Optimization implementation on Safety Gym☆23Updated 3 years ago
- Implementation of "Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning" (https://arxiv.org/pdf/1712.08266.pdf)☆37Updated 6 years ago
- PyTorch implementation of Constrained Policy Optimization☆50Updated 3 years ago
- Hybrid action space reinforcement learning algorithms.☆12Updated 3 years ago
- Implementation of Hierarchical Deep Q-Learning (Kulkarni et al., 2016)☆34Updated 5 years ago
- Implementation of Multi-Agent Reinforcement Learning algorithm(s). Currently includes: MADDPG☆64Updated 5 years ago
- Value-Decomposition Networks For Cooperative Multi-Agent Learning☆21Updated 3 years ago
- Codes for the paper "HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism"☆21Updated 2 years ago
- Simple implementation for Constrained Policy Optimization in Pytorch☆15Updated 2 years ago
- scalable multi agents reinforcement learning☆54Updated 6 years ago
- Code for Dynamic Weights in Multi-Objective Deep Reinforcement Learning☆90Updated last year
- code implementation for 'Bi-level Actor-Critic for Multi-agent Coordination'(AAAI2020)☆55Updated 4 years ago
- Implementation code for GraphMIX: Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning☆29Updated 3 years ago
- Value-Decomposition Multi-Agent Actor-Critics☆40Updated 2 years ago
- Implementation of DyMA-CL, MARL algorithm☆26Updated 4 years ago
- Experimenting with meta-learning approaches to opponent modelling in MARL. Building upon previous public implementations of MADDPG and M3…☆14Updated 2 years ago
- Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.☆60Updated 2 years ago
- Bayesian Soft Actor Critic☆15Updated 2 years ago
- ICML 2019 RL for Real Life Workshop: Recurrent MADDPG for Partially Observable and Limited Communication Settings☆43Updated 5 years ago
- BranchingDQN☆49Updated 5 years ago
- Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space☆41Updated 2 years ago
- Hierarchical-DQN in pytorch (not actively maintained)☆70Updated 7 years ago
- Some multiagent deep reinforcement learning algorithms and its PyTorch implementation.☆11Updated 4 years ago
- ☆15Updated 5 years ago