facebookresearch / controllable_agent
The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Forward-Backward representation.
☆61Updated last year
Alternatives and similar repositories for controllable_agent:
Users that are interested in controllable_agent are comparing it to the libraries listed below
- ☆42Updated last year
- ExORL: Exploratory Data for Offline Reinforcement Learning☆109Updated 3 years ago
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery☆80Updated 2 years ago
- Deep Hierarchical Planning from Pixels☆94Updated 2 years ago
- Proto-RL: Reinforcement Learning with Prototypical Representations☆82Updated 2 years ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆87Updated last year
- Evaluating long-term memory of reinforcement learning algorithms☆140Updated last year
- Reinforcement Learning via Supervised Learning☆70Updated 2 years ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆43Updated 11 months ago
- Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.☆104Updated last year
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆85Updated last year
- A benchmark for offline goal-conditioned RL and offline RL☆114Updated this week
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆55Updated 10 months ago
- ☆42Updated 4 years ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆76Updated 2 months ago
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆98Updated 8 months ago
- EARL: Environment for Autonomous Reinforcement Learning☆36Updated 2 years ago
- Skeleton for scalable and flexible Jax RL implementations☆71Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆61Updated last year
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆80Updated last year
- Transformer-based World Models☆76Updated last year
- Code for "Learning to Reach Goals via Iterated Supervised Learning"☆76Updated 2 years ago
- The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)☆76Updated last year
- ☆26Updated last year
- ☆70Updated 4 months ago
- My Body Is A Cage☆39Updated 3 years ago
- ☆31Updated 10 months ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆68Updated last month
- Goal-Conditioned Reinforcement Learning with JAX☆120Updated this week
- [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and …☆37Updated 11 months ago