Emerge-Lab / nocturne_lab
A data-driven, fast driving simulator for multi-agent coordination under partial observability.
☆19Updated 3 weeks ago
Related projects: ⓘ
- ☆15Updated 10 months ago
- [ICLR 2022] Official implementation of paper: Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization☆41Updated last year
- [CoRL 2021] Official implementation of paper "Safe Driving via Expert Guided Policy Optimization".☆39Updated 5 months ago
- [CoRL'20] Learning a Decision Module by Imitating Driver’s Control Behaviors☆29Updated 2 years ago
- Learning Off-Policy with Online Planning [CoRL 2021 Best Paper Finalist]☆32Updated 2 years ago
- Official repository for paper "Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching" (ICML…☆25Updated last year
- TorchDriveEnv is a lightweight 2D driving reinforcement learning environment, supported by a solid simulator and smart non-playable chara…☆20Updated this week
- [NeurIPS 2022] Official implementation of the paper: "Human-AI Shared Control via Policy Dissection"☆48Updated last year
- An easy to understand implementation of the paper "Model-Based Reinforcement Learning for Atari"☆14Updated 4 years ago
- [ICLR 2023] The official code for paper "Guarded Policy Optimization with Imperfect Online Demonstrations"☆12Updated last year
- ☆18Updated 2 years ago
- Reimplementation (currently partial) of Deep Imitative Models paper, ICLR '20☆72Updated last year
- SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.☆52Updated 5 months ago
- Implementation of the DreamerV2 agent in torch☆11Updated 2 years ago
- Heterogeneous Multi-agent Version of Highway-env☆13Updated last year
- ☆38Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆10Updated last year
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆49Updated 8 months ago
- (NeurIPS 2023) Residual Q-Learning: Offline and Online Policy Customization without Value☆27Updated 5 months ago
- Literature and code for inverse reinforcement leanring research☆24Updated 4 years ago
- This is the official implementation of NeurIPS 2022 paper "Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal R…☆30Updated last year
- Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.☆90Updated last year
- ☆12Updated last year
- Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning☆20Updated 6 months ago
- Agents code for Multi-Agent Connected Autonomous Driving (MACAD) described in the paper presented in the Machine Learning for Autonomous …☆24Updated 3 years ago
- ☆16Updated last year
- Official release for the code used in paper: Learning from Active Human Involvement through Proxy Value Propagation (NeurIPS 2023 Spotlig…☆22Updated 3 months ago
- [TPAMI, 2023] Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving☆34Updated 8 months ago
- Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL☆25Updated 10 months ago
- ☆18Updated 3 years ago