google-deepmind / agent_debugger
Causal Analysis of Agent Behavior for AI Safety
☆17Updated last year
Related projects: ⓘ
- GPT implementation in Flax☆18Updated 2 years ago
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆30Updated 11 months ago
- ☆17Updated 3 months ago
- ☆17Updated last year
- ☆11Updated 2 months ago
- ☆15Updated 2 years ago
- Implementation of BC-IRL and other IRL baselines☆25Updated last year
- A web based platform for collecting human actions in reinforcement learning environments☆26Updated last year
- Repo to reproduce the First-Explore paper results☆36Updated last year
- ☆29Updated 2 years ago
- Repository for "Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics" …☆12Updated 3 months ago
- AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.☆31Updated 8 months ago
- A PyTorch Implementation of PlaNet: A Deep Planning Network for Reinforcement Learning☆11Updated 4 years ago
- Official code for "Reward-Free Curricula for Training Robust World Models", ICLR 2024.☆25Updated 7 months ago
- Coherent Soft Imitation Learning☆16Updated last month
- ☆33Updated last year
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- ☆28Updated 2 years ago
- An Open-Ended Agentic Simulator☆17Updated last month
- ☆16Updated this week
- Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories☆41Updated last year
- Minimal Decision Transformer Implementation written in Jax (Flax).☆17Updated 2 years ago
- flexible meta-learning in jax☆12Updated 11 months ago
- PyTorch Package For Quasimetric Learning☆38Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code☆20Updated 3 weeks ago
- ☆25Updated last week
- Scalable Opponent Shaping Experiments in JAX☆19Updated 5 months ago
- Code for the paper Task Agnostic Morphology Evolution.☆20Updated 3 years ago
- PyTorch implementation for "Discovery of Incremental Skills" (DISk) algorithm from ICLR 2022 paper "One After Another: Learning Increment…☆18Updated 2 years ago
- Accelerated replay buffers in JAX☆39Updated 2 years ago