facebookresearch / controllable_agentLinks
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.
☆70Updated 2 years ago
Alternatives and similar repositories for controllable_agent
Users that are interested in controllable_agent are comparing it to the libraries listed below
Sorting:
- ☆52Updated 2 years ago
- ExORL: Exploratory Data for Offline Reinforcement Learning☆120Updated 3 years ago
- Deep Hierarchical Planning from Pixels☆112Updated 3 years ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated 2 years ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆57Updated last year
- Code for "Learning to Reach Goals via Iterated Supervised Learning"☆81Updated 3 years ago
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery☆83Updated 3 years ago
- Reinforcement Learning via Supervised Learning☆72Updated 3 years ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆86Updated last year
- Fast reinforcement learning research☆61Updated last year
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆82Updated 2 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆160Updated 2 years ago
- Skeleton for scalable and flexible Jax RL implementations☆92Updated 2 years ago
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆112Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆81Updated 2 years ago
- off-policy RL on long sequences☆155Updated 4 months ago
- Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023☆50Updated 7 months ago
- Proto-RL: Reinforcement Learning with Prototypical Representations☆85Updated 3 years ago
- EARL: Environment for Autonomous Reinforcement Learning☆37Updated 3 years ago
- Conservative Q learning in Jax☆56Updated 2 years ago
- Predictable MDP Abstraction for Unsupervised Model-Based RL (ICML 2023)☆32Updated 2 years ago
- Transformer-based World Models☆86Updated 2 years ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆92Updated last year
- Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)☆127Updated last year
- ☆43Updated last year
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆103Updated 3 years ago
- My Body Is A Cage☆41Updated 4 years ago
- Extreme Q-Learning: Max Entropy RL without Entropy☆87Updated 2 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆120Updated last year
- ☆72Updated 3 years ago