{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/temporal-difference-learning-using","title":"Temporal-Difference Learning Using Distributed Error Signals","arxiv_id":"2411.03604","date":"2024-11-06","proceeding":null,"authors":["Jonas Guan","Shon Eduard Verch","Claas Voelcker","Ethan C. Jackson","Nicolas Papernot","William A. Cunningham"],"abstract":"A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.","url_abs":"https://arxiv.org/abs/2411.03604v1","url_pdf":"https://arxiv.org/pdf/2411.03604v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"temporal-difference-learning-using","repo_url":"https://github.com/social-ai-uoft/ad-paper","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.03604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03604"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/kenjyoung/MinAtar","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/social-ai-uoft/ad-paper","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google/jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-deepmind/dm_control","reach":null}],"summary":{"ran":6,"ran_honours":1,"unverified":17},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"found_in_text":{"samples":21,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2084aa5b3266ab8f","entry":"add_abstract","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_util.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2084aa5b3266ab8f"}},{"code_sha256_prefix":"cac8281b61c863de","entry":"blocked_fold_in","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/blocked_sampler.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/blocked_sampler.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cac8281b61c863de"}},{"code_sha256_prefix":"29226c63dfc413f0","entry":"buffer_callback","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/buffer_callback.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/buffer_callback.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29226c63dfc413f0"}},{"code_sha256_prefix":"9910e2fc297f8665","entry":"identity","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_checkpoint.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_checkpoint.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9910e2fc297f8665"}},{"code_sha256_prefix":"810b7a396afb59d3","entry":"offload_dot_with_no_batch_dims","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_checkpoint.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_checkpoint.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"810b7a396afb59d3"}},{"code_sha256_prefix":"90d492383f675799","entry":"sample_block","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/blocked_sampler.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/blocked_sampler.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90d492383f675799"}},{"code_sha256_prefix":"2e107afaca8a349d","entry":"save_from_both_policies","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_checkpoint.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_checkpoint.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e107afaca8a349d"}},{"code_sha256_prefix":"7dc8234c8244b402","entry":"add_impl","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7dc8234c8244b402"}},{"code_sha256_prefix":"c4008ce797ce88b7","entry":"add_jaxvals","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c4008ce797ce88b7"}},{"code_sha256_prefix":"0e74585505a2eea7","entry":"argnums_partial","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/api_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/api_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e74585505a2eea7"}},{"code_sha256_prefix":"8b0add7ca6f2c489","entry":"dots_saveable","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_checkpoint.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b0add7ca6f2c489"}},{"code_sha256_prefix":"23b150f55677eecf","entry":"dots_with_no_batch_dims_saveable","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/ad_checkpoint.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/ad_checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23b150f55677eecf"}},{"code_sha256_prefix":"eb71d064139c0c1e","entry":"flatten_fun","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/api_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/api_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb71d064139c0c1e"}},{"code_sha256_prefix":"3ccc19e76d1ee880","entry":"flatten_fun_nokwargs","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/api_util.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/api_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ccc19e76d1ee880"}},{"code_sha256_prefix":"9fc0e9452ec7806b","entry":"get","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/cache_key.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/cache_key.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fc0e9452ec7806b"}},{"code_sha256_prefix":"e16eeb112aeeb02b","entry":"get_quantile_at_action","repo":"social-ai-uoft/ad-paper","repo_kind":"official","path":"src/artificial_dopamine/algorithms/ad_qrdqn.py","file_url":"https://github.com/social-ai-uoft/ad-paper/blob/HEAD/src/artificial_dopamine/algorithms/ad_qrdqn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e16eeb112aeeb02b"}},{"code_sha256_prefix":"32ccda7b7e95f774","entry":"huber","repo":"social-ai-uoft/ad-paper","repo_kind":"official","path":"src/artificial_dopamine/algorithms/ad_qrdqn.py","file_url":"https://github.com/social-ai-uoft/ad-paper/blob/HEAD/src/artificial_dopamine/algorithms/ad_qrdqn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32ccda7b7e95f774"}},{"code_sha256_prefix":"a3183105bcb38a23","entry":"io_callback_batching_rule","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/callback.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/callback.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3183105bcb38a23"}},{"code_sha256_prefix":"1dc34cecff86ce05","entry":"jit","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/api.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/api.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1dc34cecff86ce05"}},{"code_sha256_prefix":"e0971622bbe8538e","entry":"jit","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/api.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0971622bbe8538e"}},{"code_sha256_prefix":"89936e0c6682decc","entry":"k_folding","repo":"social-ai-uoft/ad-paper","repo_kind":"official","path":"src/artificial_dopamine/ad_layers.py","file_url":"https://github.com/social-ai-uoft/ad-paper/blob/HEAD/src/artificial_dopamine/ad_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89936e0c6682decc"}},{"code_sha256_prefix":"a860c143f6dbe657","entry":"pure_callback","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/callback.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/callback.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a860c143f6dbe657"}},{"code_sha256_prefix":"21ed500dc8476b88","entry":"pure_callback","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/callback.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/callback.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21ed500dc8476b88"}},{"code_sha256_prefix":"55ac98a7c46161c0","entry":"pure_callback_lowering","repo":"google/jax","repo_kind":"found_in_text","path":"jax/_src/callback.py","file_url":"https://github.com/google/jax/blob/HEAD/jax/_src/callback.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55ac98a7c46161c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}