SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.06070 · 2018

Diversity is All You Need: Learning Skills without a Reward Function

Abhishek Gupta, Benjamin Eysenbach, Julian Google, Brain Levine

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

FunctionStatusWhere it lives
Discriminator Ran alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("6cb01147c4e509a3")
Memory Ran alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("b9f1643b2317c893")
PolicyNetwork Ran alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("f94f400f8198fffa")
QvalueNetwork Ran alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("80c6f43e5b975034")
ValueNetwork Ran alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("7149f4b47fc8f92f")
SACAgent Not yet run alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("b5094696507eef80")
init_weight Not yet run alirezakazemipour/DIAYN-PyTorch/Brain/agent.py
code served (permissive licence) · get_code("5abea37f033582d3")
normalize_env Not yet run navneet-nmk/Hierarchical-Meta-Reinforcement-Learning/maml_rl/envs/normalized_env.py
code served (permissive licence) · get_code("430c8be20a33317f")
total_rewards Not yet run navneet-nmk/Hierarchical-Meta-Reinforcement-Learning/t_maml_rl.py
code served (permissive licence) · get_code("e70b539f75e44f24")
value_iteration Not yet run navneet-nmk/Hierarchical-Meta-Reinforcement-Learning/maml_rl/utils/reinforcement_learning.py
code served (permissive licence) · get_code("9bb3898b9bf31939")
value_iteration_finite_horizon Not yet run navneet-nmk/Hierarchical-Meta-Reinforcement-Learning/maml_rl/utils/reinforcement_learning.py
code served (permissive licence) · get_code("788406b2cba7e7a9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose "Diversity is All You Need"(DIAYN), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill that solves the benchmark task despite never receiving the true task reward. We show how pretrained skills can provide a good parameter initialization for downstream tasks, and can be composed hierarchically to solve complex, sparse reward tasks. Our results suggest that unsupervised discovery of skills can serve as an effective pretraining mechanism for overcoming challenges of exploration and data efficiency in reinforcement learning. * Work done as a member of the Google AI Residency Program (g.co/airesidency).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1802.06070")
get_code_for_paper("1802.06070")
have("1802.06070")

Connect an agent — have() is free.